Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- merges.txt +0 -0
- mlc-chat-config.json +86 -0
- ndarray-cache-b16.json +2614 -0
- ndarray-cache.json +2614 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
- params_shard_22.bin +3 -0
- params_shard_23.bin +3 -0
- params_shard_24.bin +3 -0
- params_shard_25.bin +3 -0
- params_shard_26.bin +3 -0
- params_shard_27.bin +3 -0
- params_shard_28.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_4.bin +3 -0
- params_shard_5.bin +3 -0
- params_shard_6.bin +3 -0
- params_shard_7.bin +3 -0
- params_shard_8.bin +3 -0
- params_shard_9.bin +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mlc-chat-config.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "qwen3",
|
4 |
+
"quantization": "q0f32",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_act": "silu",
|
7 |
+
"hidden_size": 1024,
|
8 |
+
"intermediate_size": 3072,
|
9 |
+
"attention_bias": false,
|
10 |
+
"num_attention_heads": 16,
|
11 |
+
"num_hidden_layers": 28,
|
12 |
+
"num_key_value_heads": 8,
|
13 |
+
"rms_norm_eps": 1e-06,
|
14 |
+
"rope_theta": 1000000,
|
15 |
+
"vocab_size": 151936,
|
16 |
+
"tie_word_embeddings": true,
|
17 |
+
"context_window_size": 40960,
|
18 |
+
"prefill_chunk_size": 2048,
|
19 |
+
"tensor_parallel_shards": 1,
|
20 |
+
"head_dim": 128,
|
21 |
+
"dtype": "float32",
|
22 |
+
"max_batch_size": 128,
|
23 |
+
"weight_block_size": null
|
24 |
+
},
|
25 |
+
"vocab_size": 151936,
|
26 |
+
"context_window_size": 40960,
|
27 |
+
"sliding_window_size": -1,
|
28 |
+
"prefill_chunk_size": 2048,
|
29 |
+
"attention_sink_size": -1,
|
30 |
+
"tensor_parallel_shards": 1,
|
31 |
+
"pipeline_parallel_stages": 1,
|
32 |
+
"temperature": 0.6,
|
33 |
+
"presence_penalty": 0.0,
|
34 |
+
"frequency_penalty": 0.0,
|
35 |
+
"repetition_penalty": 1.0,
|
36 |
+
"top_p": 0.95,
|
37 |
+
"tokenizer_files": [
|
38 |
+
"tokenizer.json",
|
39 |
+
"vocab.json",
|
40 |
+
"merges.txt",
|
41 |
+
"tokenizer_config.json"
|
42 |
+
],
|
43 |
+
"tokenizer_info": {
|
44 |
+
"token_postproc_method": "byte_level",
|
45 |
+
"prepend_space_in_encode": false,
|
46 |
+
"strip_space_in_decode": false
|
47 |
+
},
|
48 |
+
"conv_template": {
|
49 |
+
"name": "qwen2",
|
50 |
+
"system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
|
51 |
+
"system_message": "You are a helpful assistant.",
|
52 |
+
"system_prefix_token_ids": null,
|
53 |
+
"add_role_after_system_message": true,
|
54 |
+
"roles": {
|
55 |
+
"user": "<|im_start|>user",
|
56 |
+
"assistant": "<|im_start|>assistant"
|
57 |
+
},
|
58 |
+
"role_templates": {
|
59 |
+
"user": "{user_message}",
|
60 |
+
"assistant": "{assistant_message}",
|
61 |
+
"tool": "{tool_message}"
|
62 |
+
},
|
63 |
+
"messages": [],
|
64 |
+
"seps": [
|
65 |
+
"<|im_end|>\n"
|
66 |
+
],
|
67 |
+
"role_content_sep": "\n",
|
68 |
+
"role_empty_sep": "\n",
|
69 |
+
"stop_str": [
|
70 |
+
"<|endoftext|>",
|
71 |
+
"<|im_end|>"
|
72 |
+
],
|
73 |
+
"stop_token_ids": [
|
74 |
+
151643,
|
75 |
+
151645
|
76 |
+
],
|
77 |
+
"function_string": "",
|
78 |
+
"use_function_calling": false
|
79 |
+
},
|
80 |
+
"pad_token_id": 151643,
|
81 |
+
"bos_token_id": 151643,
|
82 |
+
"eos_token_id": [
|
83 |
+
151645,
|
84 |
+
151643
|
85 |
+
]
|
86 |
+
}
|
ndarray-cache-b16.json
ADDED
@@ -0,0 +1,2614 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"ParamSize": 226,
|
4 |
+
"ParamBytes": 2384199680.0,
|
5 |
+
"BitsPerParam": 25.37623158078298
|
6 |
+
},
|
7 |
+
"records": [
|
8 |
+
{
|
9 |
+
"dataPath": "params_shard_0.bin",
|
10 |
+
"format": "raw-shard",
|
11 |
+
"nbytes": 311164928,
|
12 |
+
"records": [
|
13 |
+
{
|
14 |
+
"name": "model.embed_tokens.weight",
|
15 |
+
"shape": [
|
16 |
+
151936,
|
17 |
+
1024
|
18 |
+
],
|
19 |
+
"dtype": "bfloat16",
|
20 |
+
"format": "raw",
|
21 |
+
"nbytes": 311164928,
|
22 |
+
"byteOffset": 0
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"md5sum": "4f615e4e204fe160829261879c8c4864"
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"dataPath": "params_shard_1.bin",
|
29 |
+
"format": "raw-shard",
|
30 |
+
"nbytes": 31463936,
|
31 |
+
"records": [
|
32 |
+
{
|
33 |
+
"name": "model.layers.0.input_layernorm.weight",
|
34 |
+
"shape": [
|
35 |
+
1024
|
36 |
+
],
|
37 |
+
"dtype": "bfloat16",
|
38 |
+
"format": "raw",
|
39 |
+
"nbytes": 2048,
|
40 |
+
"byteOffset": 0
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"name": "model.layers.0.mlp.down_proj.weight",
|
44 |
+
"shape": [
|
45 |
+
1024,
|
46 |
+
3072
|
47 |
+
],
|
48 |
+
"dtype": "bfloat16",
|
49 |
+
"format": "raw",
|
50 |
+
"nbytes": 6291456,
|
51 |
+
"byteOffset": 2048
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"name": "model.layers.0.mlp.gate_up_proj.weight",
|
55 |
+
"shape": [
|
56 |
+
6144,
|
57 |
+
1024
|
58 |
+
],
|
59 |
+
"dtype": "bfloat16",
|
60 |
+
"format": "raw",
|
61 |
+
"nbytes": 12582912,
|
62 |
+
"byteOffset": 6293504
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
66 |
+
"shape": [
|
67 |
+
1024
|
68 |
+
],
|
69 |
+
"dtype": "bfloat16",
|
70 |
+
"format": "raw",
|
71 |
+
"nbytes": 2048,
|
72 |
+
"byteOffset": 18876416
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"name": "model.layers.0.self_attn.k_norm.weight",
|
76 |
+
"shape": [
|
77 |
+
128
|
78 |
+
],
|
79 |
+
"dtype": "bfloat16",
|
80 |
+
"format": "raw",
|
81 |
+
"nbytes": 256,
|
82 |
+
"byteOffset": 18878464
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"name": "model.layers.0.self_attn.c_attn.weight",
|
86 |
+
"shape": [
|
87 |
+
4096,
|
88 |
+
1024
|
89 |
+
],
|
90 |
+
"dtype": "bfloat16",
|
91 |
+
"format": "raw",
|
92 |
+
"nbytes": 8388608,
|
93 |
+
"byteOffset": 18878720
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"name": "model.layers.0.self_attn.o_proj.weight",
|
97 |
+
"shape": [
|
98 |
+
1024,
|
99 |
+
2048
|
100 |
+
],
|
101 |
+
"dtype": "bfloat16",
|
102 |
+
"format": "raw",
|
103 |
+
"nbytes": 4194304,
|
104 |
+
"byteOffset": 27267328
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"name": "model.layers.0.self_attn.q_norm.weight",
|
108 |
+
"shape": [
|
109 |
+
128
|
110 |
+
],
|
111 |
+
"dtype": "bfloat16",
|
112 |
+
"format": "raw",
|
113 |
+
"nbytes": 256,
|
114 |
+
"byteOffset": 31461632
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"name": "model.layers.1.input_layernorm.weight",
|
118 |
+
"shape": [
|
119 |
+
1024
|
120 |
+
],
|
121 |
+
"dtype": "bfloat16",
|
122 |
+
"format": "raw",
|
123 |
+
"nbytes": 2048,
|
124 |
+
"byteOffset": 31461888
|
125 |
+
}
|
126 |
+
],
|
127 |
+
"md5sum": "9e8c92fad1c6d7956d2f76d18b34c0c0"
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"dataPath": "params_shard_2.bin",
|
131 |
+
"format": "raw-shard",
|
132 |
+
"nbytes": 31461888,
|
133 |
+
"records": [
|
134 |
+
{
|
135 |
+
"name": "model.layers.1.mlp.down_proj.weight",
|
136 |
+
"shape": [
|
137 |
+
1024,
|
138 |
+
3072
|
139 |
+
],
|
140 |
+
"dtype": "bfloat16",
|
141 |
+
"format": "raw",
|
142 |
+
"nbytes": 6291456,
|
143 |
+
"byteOffset": 0
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"name": "model.layers.1.mlp.gate_up_proj.weight",
|
147 |
+
"shape": [
|
148 |
+
6144,
|
149 |
+
1024
|
150 |
+
],
|
151 |
+
"dtype": "bfloat16",
|
152 |
+
"format": "raw",
|
153 |
+
"nbytes": 12582912,
|
154 |
+
"byteOffset": 6291456
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
158 |
+
"shape": [
|
159 |
+
1024
|
160 |
+
],
|
161 |
+
"dtype": "bfloat16",
|
162 |
+
"format": "raw",
|
163 |
+
"nbytes": 2048,
|
164 |
+
"byteOffset": 18874368
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"name": "model.layers.1.self_attn.k_norm.weight",
|
168 |
+
"shape": [
|
169 |
+
128
|
170 |
+
],
|
171 |
+
"dtype": "bfloat16",
|
172 |
+
"format": "raw",
|
173 |
+
"nbytes": 256,
|
174 |
+
"byteOffset": 18876416
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"name": "model.layers.1.self_attn.c_attn.weight",
|
178 |
+
"shape": [
|
179 |
+
4096,
|
180 |
+
1024
|
181 |
+
],
|
182 |
+
"dtype": "bfloat16",
|
183 |
+
"format": "raw",
|
184 |
+
"nbytes": 8388608,
|
185 |
+
"byteOffset": 18876672
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"name": "model.layers.1.self_attn.o_proj.weight",
|
189 |
+
"shape": [
|
190 |
+
1024,
|
191 |
+
2048
|
192 |
+
],
|
193 |
+
"dtype": "bfloat16",
|
194 |
+
"format": "raw",
|
195 |
+
"nbytes": 4194304,
|
196 |
+
"byteOffset": 27265280
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"name": "model.layers.1.self_attn.q_norm.weight",
|
200 |
+
"shape": [
|
201 |
+
128
|
202 |
+
],
|
203 |
+
"dtype": "bfloat16",
|
204 |
+
"format": "raw",
|
205 |
+
"nbytes": 256,
|
206 |
+
"byteOffset": 31459584
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"name": "model.layers.10.input_layernorm.weight",
|
210 |
+
"shape": [
|
211 |
+
1024
|
212 |
+
],
|
213 |
+
"dtype": "bfloat16",
|
214 |
+
"format": "raw",
|
215 |
+
"nbytes": 2048,
|
216 |
+
"byteOffset": 31459840
|
217 |
+
}
|
218 |
+
],
|
219 |
+
"md5sum": "c74facda8699fab5c1fb909a0038eac3"
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"dataPath": "params_shard_3.bin",
|
223 |
+
"format": "raw-shard",
|
224 |
+
"nbytes": 31461888,
|
225 |
+
"records": [
|
226 |
+
{
|
227 |
+
"name": "model.layers.10.mlp.down_proj.weight",
|
228 |
+
"shape": [
|
229 |
+
1024,
|
230 |
+
3072
|
231 |
+
],
|
232 |
+
"dtype": "bfloat16",
|
233 |
+
"format": "raw",
|
234 |
+
"nbytes": 6291456,
|
235 |
+
"byteOffset": 0
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"name": "model.layers.10.mlp.gate_up_proj.weight",
|
239 |
+
"shape": [
|
240 |
+
6144,
|
241 |
+
1024
|
242 |
+
],
|
243 |
+
"dtype": "bfloat16",
|
244 |
+
"format": "raw",
|
245 |
+
"nbytes": 12582912,
|
246 |
+
"byteOffset": 6291456
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
250 |
+
"shape": [
|
251 |
+
1024
|
252 |
+
],
|
253 |
+
"dtype": "bfloat16",
|
254 |
+
"format": "raw",
|
255 |
+
"nbytes": 2048,
|
256 |
+
"byteOffset": 18874368
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"name": "model.layers.10.self_attn.k_norm.weight",
|
260 |
+
"shape": [
|
261 |
+
128
|
262 |
+
],
|
263 |
+
"dtype": "bfloat16",
|
264 |
+
"format": "raw",
|
265 |
+
"nbytes": 256,
|
266 |
+
"byteOffset": 18876416
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"name": "model.layers.10.self_attn.c_attn.weight",
|
270 |
+
"shape": [
|
271 |
+
4096,
|
272 |
+
1024
|
273 |
+
],
|
274 |
+
"dtype": "bfloat16",
|
275 |
+
"format": "raw",
|
276 |
+
"nbytes": 8388608,
|
277 |
+
"byteOffset": 18876672
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"name": "model.layers.10.self_attn.o_proj.weight",
|
281 |
+
"shape": [
|
282 |
+
1024,
|
283 |
+
2048
|
284 |
+
],
|
285 |
+
"dtype": "bfloat16",
|
286 |
+
"format": "raw",
|
287 |
+
"nbytes": 4194304,
|
288 |
+
"byteOffset": 27265280
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"name": "model.layers.10.self_attn.q_norm.weight",
|
292 |
+
"shape": [
|
293 |
+
128
|
294 |
+
],
|
295 |
+
"dtype": "bfloat16",
|
296 |
+
"format": "raw",
|
297 |
+
"nbytes": 256,
|
298 |
+
"byteOffset": 31459584
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"name": "model.layers.11.input_layernorm.weight",
|
302 |
+
"shape": [
|
303 |
+
1024
|
304 |
+
],
|
305 |
+
"dtype": "bfloat16",
|
306 |
+
"format": "raw",
|
307 |
+
"nbytes": 2048,
|
308 |
+
"byteOffset": 31459840
|
309 |
+
}
|
310 |
+
],
|
311 |
+
"md5sum": "79511a618a11a839e255c0d6b8117701"
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"dataPath": "params_shard_4.bin",
|
315 |
+
"format": "raw-shard",
|
316 |
+
"nbytes": 31461888,
|
317 |
+
"records": [
|
318 |
+
{
|
319 |
+
"name": "model.layers.11.mlp.down_proj.weight",
|
320 |
+
"shape": [
|
321 |
+
1024,
|
322 |
+
3072
|
323 |
+
],
|
324 |
+
"dtype": "bfloat16",
|
325 |
+
"format": "raw",
|
326 |
+
"nbytes": 6291456,
|
327 |
+
"byteOffset": 0
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"name": "model.layers.11.mlp.gate_up_proj.weight",
|
331 |
+
"shape": [
|
332 |
+
6144,
|
333 |
+
1024
|
334 |
+
],
|
335 |
+
"dtype": "bfloat16",
|
336 |
+
"format": "raw",
|
337 |
+
"nbytes": 12582912,
|
338 |
+
"byteOffset": 6291456
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
342 |
+
"shape": [
|
343 |
+
1024
|
344 |
+
],
|
345 |
+
"dtype": "bfloat16",
|
346 |
+
"format": "raw",
|
347 |
+
"nbytes": 2048,
|
348 |
+
"byteOffset": 18874368
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"name": "model.layers.11.self_attn.k_norm.weight",
|
352 |
+
"shape": [
|
353 |
+
128
|
354 |
+
],
|
355 |
+
"dtype": "bfloat16",
|
356 |
+
"format": "raw",
|
357 |
+
"nbytes": 256,
|
358 |
+
"byteOffset": 18876416
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"name": "model.layers.11.self_attn.c_attn.weight",
|
362 |
+
"shape": [
|
363 |
+
4096,
|
364 |
+
1024
|
365 |
+
],
|
366 |
+
"dtype": "bfloat16",
|
367 |
+
"format": "raw",
|
368 |
+
"nbytes": 8388608,
|
369 |
+
"byteOffset": 18876672
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"name": "model.layers.11.self_attn.o_proj.weight",
|
373 |
+
"shape": [
|
374 |
+
1024,
|
375 |
+
2048
|
376 |
+
],
|
377 |
+
"dtype": "bfloat16",
|
378 |
+
"format": "raw",
|
379 |
+
"nbytes": 4194304,
|
380 |
+
"byteOffset": 27265280
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"name": "model.layers.11.self_attn.q_norm.weight",
|
384 |
+
"shape": [
|
385 |
+
128
|
386 |
+
],
|
387 |
+
"dtype": "bfloat16",
|
388 |
+
"format": "raw",
|
389 |
+
"nbytes": 256,
|
390 |
+
"byteOffset": 31459584
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"name": "model.layers.12.input_layernorm.weight",
|
394 |
+
"shape": [
|
395 |
+
1024
|
396 |
+
],
|
397 |
+
"dtype": "bfloat16",
|
398 |
+
"format": "raw",
|
399 |
+
"nbytes": 2048,
|
400 |
+
"byteOffset": 31459840
|
401 |
+
}
|
402 |
+
],
|
403 |
+
"md5sum": "340f19886367858e06bb5b5367d20305"
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"dataPath": "params_shard_5.bin",
|
407 |
+
"format": "raw-shard",
|
408 |
+
"nbytes": 31461888,
|
409 |
+
"records": [
|
410 |
+
{
|
411 |
+
"name": "model.layers.12.mlp.down_proj.weight",
|
412 |
+
"shape": [
|
413 |
+
1024,
|
414 |
+
3072
|
415 |
+
],
|
416 |
+
"dtype": "bfloat16",
|
417 |
+
"format": "raw",
|
418 |
+
"nbytes": 6291456,
|
419 |
+
"byteOffset": 0
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"name": "model.layers.12.mlp.gate_up_proj.weight",
|
423 |
+
"shape": [
|
424 |
+
6144,
|
425 |
+
1024
|
426 |
+
],
|
427 |
+
"dtype": "bfloat16",
|
428 |
+
"format": "raw",
|
429 |
+
"nbytes": 12582912,
|
430 |
+
"byteOffset": 6291456
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
434 |
+
"shape": [
|
435 |
+
1024
|
436 |
+
],
|
437 |
+
"dtype": "bfloat16",
|
438 |
+
"format": "raw",
|
439 |
+
"nbytes": 2048,
|
440 |
+
"byteOffset": 18874368
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"name": "model.layers.12.self_attn.k_norm.weight",
|
444 |
+
"shape": [
|
445 |
+
128
|
446 |
+
],
|
447 |
+
"dtype": "bfloat16",
|
448 |
+
"format": "raw",
|
449 |
+
"nbytes": 256,
|
450 |
+
"byteOffset": 18876416
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"name": "model.layers.12.self_attn.c_attn.weight",
|
454 |
+
"shape": [
|
455 |
+
4096,
|
456 |
+
1024
|
457 |
+
],
|
458 |
+
"dtype": "bfloat16",
|
459 |
+
"format": "raw",
|
460 |
+
"nbytes": 8388608,
|
461 |
+
"byteOffset": 18876672
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"name": "model.layers.12.self_attn.o_proj.weight",
|
465 |
+
"shape": [
|
466 |
+
1024,
|
467 |
+
2048
|
468 |
+
],
|
469 |
+
"dtype": "bfloat16",
|
470 |
+
"format": "raw",
|
471 |
+
"nbytes": 4194304,
|
472 |
+
"byteOffset": 27265280
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"name": "model.layers.12.self_attn.q_norm.weight",
|
476 |
+
"shape": [
|
477 |
+
128
|
478 |
+
],
|
479 |
+
"dtype": "bfloat16",
|
480 |
+
"format": "raw",
|
481 |
+
"nbytes": 256,
|
482 |
+
"byteOffset": 31459584
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"name": "model.layers.13.input_layernorm.weight",
|
486 |
+
"shape": [
|
487 |
+
1024
|
488 |
+
],
|
489 |
+
"dtype": "bfloat16",
|
490 |
+
"format": "raw",
|
491 |
+
"nbytes": 2048,
|
492 |
+
"byteOffset": 31459840
|
493 |
+
}
|
494 |
+
],
|
495 |
+
"md5sum": "051d820dffb4d079fe6324e4fed50c4f"
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"dataPath": "params_shard_6.bin",
|
499 |
+
"format": "raw-shard",
|
500 |
+
"nbytes": 31461888,
|
501 |
+
"records": [
|
502 |
+
{
|
503 |
+
"name": "model.layers.13.mlp.down_proj.weight",
|
504 |
+
"shape": [
|
505 |
+
1024,
|
506 |
+
3072
|
507 |
+
],
|
508 |
+
"dtype": "bfloat16",
|
509 |
+
"format": "raw",
|
510 |
+
"nbytes": 6291456,
|
511 |
+
"byteOffset": 0
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"name": "model.layers.13.mlp.gate_up_proj.weight",
|
515 |
+
"shape": [
|
516 |
+
6144,
|
517 |
+
1024
|
518 |
+
],
|
519 |
+
"dtype": "bfloat16",
|
520 |
+
"format": "raw",
|
521 |
+
"nbytes": 12582912,
|
522 |
+
"byteOffset": 6291456
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
526 |
+
"shape": [
|
527 |
+
1024
|
528 |
+
],
|
529 |
+
"dtype": "bfloat16",
|
530 |
+
"format": "raw",
|
531 |
+
"nbytes": 2048,
|
532 |
+
"byteOffset": 18874368
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"name": "model.layers.13.self_attn.k_norm.weight",
|
536 |
+
"shape": [
|
537 |
+
128
|
538 |
+
],
|
539 |
+
"dtype": "bfloat16",
|
540 |
+
"format": "raw",
|
541 |
+
"nbytes": 256,
|
542 |
+
"byteOffset": 18876416
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"name": "model.layers.13.self_attn.c_attn.weight",
|
546 |
+
"shape": [
|
547 |
+
4096,
|
548 |
+
1024
|
549 |
+
],
|
550 |
+
"dtype": "bfloat16",
|
551 |
+
"format": "raw",
|
552 |
+
"nbytes": 8388608,
|
553 |
+
"byteOffset": 18876672
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"name": "model.layers.13.self_attn.o_proj.weight",
|
557 |
+
"shape": [
|
558 |
+
1024,
|
559 |
+
2048
|
560 |
+
],
|
561 |
+
"dtype": "bfloat16",
|
562 |
+
"format": "raw",
|
563 |
+
"nbytes": 4194304,
|
564 |
+
"byteOffset": 27265280
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"name": "model.layers.13.self_attn.q_norm.weight",
|
568 |
+
"shape": [
|
569 |
+
128
|
570 |
+
],
|
571 |
+
"dtype": "bfloat16",
|
572 |
+
"format": "raw",
|
573 |
+
"nbytes": 256,
|
574 |
+
"byteOffset": 31459584
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"name": "model.layers.14.input_layernorm.weight",
|
578 |
+
"shape": [
|
579 |
+
1024
|
580 |
+
],
|
581 |
+
"dtype": "bfloat16",
|
582 |
+
"format": "raw",
|
583 |
+
"nbytes": 2048,
|
584 |
+
"byteOffset": 31459840
|
585 |
+
}
|
586 |
+
],
|
587 |
+
"md5sum": "4aa584075dc763c62cfe3d5e58f17506"
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"dataPath": "params_shard_7.bin",
|
591 |
+
"format": "raw-shard",
|
592 |
+
"nbytes": 31461888,
|
593 |
+
"records": [
|
594 |
+
{
|
595 |
+
"name": "model.layers.14.mlp.down_proj.weight",
|
596 |
+
"shape": [
|
597 |
+
1024,
|
598 |
+
3072
|
599 |
+
],
|
600 |
+
"dtype": "bfloat16",
|
601 |
+
"format": "raw",
|
602 |
+
"nbytes": 6291456,
|
603 |
+
"byteOffset": 0
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"name": "model.layers.14.mlp.gate_up_proj.weight",
|
607 |
+
"shape": [
|
608 |
+
6144,
|
609 |
+
1024
|
610 |
+
],
|
611 |
+
"dtype": "bfloat16",
|
612 |
+
"format": "raw",
|
613 |
+
"nbytes": 12582912,
|
614 |
+
"byteOffset": 6291456
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"name": "model.layers.14.post_attention_layernorm.weight",
|
618 |
+
"shape": [
|
619 |
+
1024
|
620 |
+
],
|
621 |
+
"dtype": "bfloat16",
|
622 |
+
"format": "raw",
|
623 |
+
"nbytes": 2048,
|
624 |
+
"byteOffset": 18874368
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"name": "model.layers.14.self_attn.k_norm.weight",
|
628 |
+
"shape": [
|
629 |
+
128
|
630 |
+
],
|
631 |
+
"dtype": "bfloat16",
|
632 |
+
"format": "raw",
|
633 |
+
"nbytes": 256,
|
634 |
+
"byteOffset": 18876416
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"name": "model.layers.14.self_attn.c_attn.weight",
|
638 |
+
"shape": [
|
639 |
+
4096,
|
640 |
+
1024
|
641 |
+
],
|
642 |
+
"dtype": "bfloat16",
|
643 |
+
"format": "raw",
|
644 |
+
"nbytes": 8388608,
|
645 |
+
"byteOffset": 18876672
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"name": "model.layers.14.self_attn.o_proj.weight",
|
649 |
+
"shape": [
|
650 |
+
1024,
|
651 |
+
2048
|
652 |
+
],
|
653 |
+
"dtype": "bfloat16",
|
654 |
+
"format": "raw",
|
655 |
+
"nbytes": 4194304,
|
656 |
+
"byteOffset": 27265280
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"name": "model.layers.14.self_attn.q_norm.weight",
|
660 |
+
"shape": [
|
661 |
+
128
|
662 |
+
],
|
663 |
+
"dtype": "bfloat16",
|
664 |
+
"format": "raw",
|
665 |
+
"nbytes": 256,
|
666 |
+
"byteOffset": 31459584
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"name": "model.layers.15.input_layernorm.weight",
|
670 |
+
"shape": [
|
671 |
+
1024
|
672 |
+
],
|
673 |
+
"dtype": "bfloat16",
|
674 |
+
"format": "raw",
|
675 |
+
"nbytes": 2048,
|
676 |
+
"byteOffset": 31459840
|
677 |
+
}
|
678 |
+
],
|
679 |
+
"md5sum": "f3846e544c925d1caab9675209fb9b72"
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"dataPath": "params_shard_8.bin",
|
683 |
+
"format": "raw-shard",
|
684 |
+
"nbytes": 31461888,
|
685 |
+
"records": [
|
686 |
+
{
|
687 |
+
"name": "model.layers.15.mlp.down_proj.weight",
|
688 |
+
"shape": [
|
689 |
+
1024,
|
690 |
+
3072
|
691 |
+
],
|
692 |
+
"dtype": "bfloat16",
|
693 |
+
"format": "raw",
|
694 |
+
"nbytes": 6291456,
|
695 |
+
"byteOffset": 0
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"name": "model.layers.15.mlp.gate_up_proj.weight",
|
699 |
+
"shape": [
|
700 |
+
6144,
|
701 |
+
1024
|
702 |
+
],
|
703 |
+
"dtype": "bfloat16",
|
704 |
+
"format": "raw",
|
705 |
+
"nbytes": 12582912,
|
706 |
+
"byteOffset": 6291456
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"name": "model.layers.15.post_attention_layernorm.weight",
|
710 |
+
"shape": [
|
711 |
+
1024
|
712 |
+
],
|
713 |
+
"dtype": "bfloat16",
|
714 |
+
"format": "raw",
|
715 |
+
"nbytes": 2048,
|
716 |
+
"byteOffset": 18874368
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"name": "model.layers.15.self_attn.k_norm.weight",
|
720 |
+
"shape": [
|
721 |
+
128
|
722 |
+
],
|
723 |
+
"dtype": "bfloat16",
|
724 |
+
"format": "raw",
|
725 |
+
"nbytes": 256,
|
726 |
+
"byteOffset": 18876416
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"name": "model.layers.15.self_attn.c_attn.weight",
|
730 |
+
"shape": [
|
731 |
+
4096,
|
732 |
+
1024
|
733 |
+
],
|
734 |
+
"dtype": "bfloat16",
|
735 |
+
"format": "raw",
|
736 |
+
"nbytes": 8388608,
|
737 |
+
"byteOffset": 18876672
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"name": "model.layers.15.self_attn.o_proj.weight",
|
741 |
+
"shape": [
|
742 |
+
1024,
|
743 |
+
2048
|
744 |
+
],
|
745 |
+
"dtype": "bfloat16",
|
746 |
+
"format": "raw",
|
747 |
+
"nbytes": 4194304,
|
748 |
+
"byteOffset": 27265280
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"name": "model.layers.15.self_attn.q_norm.weight",
|
752 |
+
"shape": [
|
753 |
+
128
|
754 |
+
],
|
755 |
+
"dtype": "bfloat16",
|
756 |
+
"format": "raw",
|
757 |
+
"nbytes": 256,
|
758 |
+
"byteOffset": 31459584
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"name": "model.layers.16.input_layernorm.weight",
|
762 |
+
"shape": [
|
763 |
+
1024
|
764 |
+
],
|
765 |
+
"dtype": "bfloat16",
|
766 |
+
"format": "raw",
|
767 |
+
"nbytes": 2048,
|
768 |
+
"byteOffset": 31459840
|
769 |
+
}
|
770 |
+
],
|
771 |
+
"md5sum": "4782b81576a4555a1f25d98dbcc3397e"
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"dataPath": "params_shard_9.bin",
|
775 |
+
"format": "raw-shard",
|
776 |
+
"nbytes": 31461888,
|
777 |
+
"records": [
|
778 |
+
{
|
779 |
+
"name": "model.layers.16.mlp.down_proj.weight",
|
780 |
+
"shape": [
|
781 |
+
1024,
|
782 |
+
3072
|
783 |
+
],
|
784 |
+
"dtype": "bfloat16",
|
785 |
+
"format": "raw",
|
786 |
+
"nbytes": 6291456,
|
787 |
+
"byteOffset": 0
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"name": "model.layers.16.mlp.gate_up_proj.weight",
|
791 |
+
"shape": [
|
792 |
+
6144,
|
793 |
+
1024
|
794 |
+
],
|
795 |
+
"dtype": "bfloat16",
|
796 |
+
"format": "raw",
|
797 |
+
"nbytes": 12582912,
|
798 |
+
"byteOffset": 6291456
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"name": "model.layers.16.post_attention_layernorm.weight",
|
802 |
+
"shape": [
|
803 |
+
1024
|
804 |
+
],
|
805 |
+
"dtype": "bfloat16",
|
806 |
+
"format": "raw",
|
807 |
+
"nbytes": 2048,
|
808 |
+
"byteOffset": 18874368
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"name": "model.layers.16.self_attn.k_norm.weight",
|
812 |
+
"shape": [
|
813 |
+
128
|
814 |
+
],
|
815 |
+
"dtype": "bfloat16",
|
816 |
+
"format": "raw",
|
817 |
+
"nbytes": 256,
|
818 |
+
"byteOffset": 18876416
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"name": "model.layers.16.self_attn.c_attn.weight",
|
822 |
+
"shape": [
|
823 |
+
4096,
|
824 |
+
1024
|
825 |
+
],
|
826 |
+
"dtype": "bfloat16",
|
827 |
+
"format": "raw",
|
828 |
+
"nbytes": 8388608,
|
829 |
+
"byteOffset": 18876672
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"name": "model.layers.16.self_attn.o_proj.weight",
|
833 |
+
"shape": [
|
834 |
+
1024,
|
835 |
+
2048
|
836 |
+
],
|
837 |
+
"dtype": "bfloat16",
|
838 |
+
"format": "raw",
|
839 |
+
"nbytes": 4194304,
|
840 |
+
"byteOffset": 27265280
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"name": "model.layers.16.self_attn.q_norm.weight",
|
844 |
+
"shape": [
|
845 |
+
128
|
846 |
+
],
|
847 |
+
"dtype": "bfloat16",
|
848 |
+
"format": "raw",
|
849 |
+
"nbytes": 256,
|
850 |
+
"byteOffset": 31459584
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"name": "model.layers.17.input_layernorm.weight",
|
854 |
+
"shape": [
|
855 |
+
1024
|
856 |
+
],
|
857 |
+
"dtype": "bfloat16",
|
858 |
+
"format": "raw",
|
859 |
+
"nbytes": 2048,
|
860 |
+
"byteOffset": 31459840
|
861 |
+
}
|
862 |
+
],
|
863 |
+
"md5sum": "50a506dc9852c1c7be39db6bbbb71bc4"
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"dataPath": "params_shard_10.bin",
|
867 |
+
"format": "raw-shard",
|
868 |
+
"nbytes": 31461888,
|
869 |
+
"records": [
|
870 |
+
{
|
871 |
+
"name": "model.layers.17.mlp.down_proj.weight",
|
872 |
+
"shape": [
|
873 |
+
1024,
|
874 |
+
3072
|
875 |
+
],
|
876 |
+
"dtype": "bfloat16",
|
877 |
+
"format": "raw",
|
878 |
+
"nbytes": 6291456,
|
879 |
+
"byteOffset": 0
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"name": "model.layers.17.mlp.gate_up_proj.weight",
|
883 |
+
"shape": [
|
884 |
+
6144,
|
885 |
+
1024
|
886 |
+
],
|
887 |
+
"dtype": "bfloat16",
|
888 |
+
"format": "raw",
|
889 |
+
"nbytes": 12582912,
|
890 |
+
"byteOffset": 6291456
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"name": "model.layers.17.post_attention_layernorm.weight",
|
894 |
+
"shape": [
|
895 |
+
1024
|
896 |
+
],
|
897 |
+
"dtype": "bfloat16",
|
898 |
+
"format": "raw",
|
899 |
+
"nbytes": 2048,
|
900 |
+
"byteOffset": 18874368
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"name": "model.layers.17.self_attn.k_norm.weight",
|
904 |
+
"shape": [
|
905 |
+
128
|
906 |
+
],
|
907 |
+
"dtype": "bfloat16",
|
908 |
+
"format": "raw",
|
909 |
+
"nbytes": 256,
|
910 |
+
"byteOffset": 18876416
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"name": "model.layers.17.self_attn.c_attn.weight",
|
914 |
+
"shape": [
|
915 |
+
4096,
|
916 |
+
1024
|
917 |
+
],
|
918 |
+
"dtype": "bfloat16",
|
919 |
+
"format": "raw",
|
920 |
+
"nbytes": 8388608,
|
921 |
+
"byteOffset": 18876672
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"name": "model.layers.17.self_attn.o_proj.weight",
|
925 |
+
"shape": [
|
926 |
+
1024,
|
927 |
+
2048
|
928 |
+
],
|
929 |
+
"dtype": "bfloat16",
|
930 |
+
"format": "raw",
|
931 |
+
"nbytes": 4194304,
|
932 |
+
"byteOffset": 27265280
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"name": "model.layers.17.self_attn.q_norm.weight",
|
936 |
+
"shape": [
|
937 |
+
128
|
938 |
+
],
|
939 |
+
"dtype": "bfloat16",
|
940 |
+
"format": "raw",
|
941 |
+
"nbytes": 256,
|
942 |
+
"byteOffset": 31459584
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"name": "model.layers.18.input_layernorm.weight",
|
946 |
+
"shape": [
|
947 |
+
1024
|
948 |
+
],
|
949 |
+
"dtype": "bfloat16",
|
950 |
+
"format": "raw",
|
951 |
+
"nbytes": 2048,
|
952 |
+
"byteOffset": 31459840
|
953 |
+
}
|
954 |
+
],
|
955 |
+
"md5sum": "28226cd94e7b0b9cb620911de11ec28c"
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"dataPath": "params_shard_11.bin",
|
959 |
+
"format": "raw-shard",
|
960 |
+
"nbytes": 31461888,
|
961 |
+
"records": [
|
962 |
+
{
|
963 |
+
"name": "model.layers.18.mlp.down_proj.weight",
|
964 |
+
"shape": [
|
965 |
+
1024,
|
966 |
+
3072
|
967 |
+
],
|
968 |
+
"dtype": "bfloat16",
|
969 |
+
"format": "raw",
|
970 |
+
"nbytes": 6291456,
|
971 |
+
"byteOffset": 0
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"name": "model.layers.18.mlp.gate_up_proj.weight",
|
975 |
+
"shape": [
|
976 |
+
6144,
|
977 |
+
1024
|
978 |
+
],
|
979 |
+
"dtype": "bfloat16",
|
980 |
+
"format": "raw",
|
981 |
+
"nbytes": 12582912,
|
982 |
+
"byteOffset": 6291456
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"name": "model.layers.18.post_attention_layernorm.weight",
|
986 |
+
"shape": [
|
987 |
+
1024
|
988 |
+
],
|
989 |
+
"dtype": "bfloat16",
|
990 |
+
"format": "raw",
|
991 |
+
"nbytes": 2048,
|
992 |
+
"byteOffset": 18874368
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"name": "model.layers.18.self_attn.k_norm.weight",
|
996 |
+
"shape": [
|
997 |
+
128
|
998 |
+
],
|
999 |
+
"dtype": "bfloat16",
|
1000 |
+
"format": "raw",
|
1001 |
+
"nbytes": 256,
|
1002 |
+
"byteOffset": 18876416
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"name": "model.layers.18.self_attn.c_attn.weight",
|
1006 |
+
"shape": [
|
1007 |
+
4096,
|
1008 |
+
1024
|
1009 |
+
],
|
1010 |
+
"dtype": "bfloat16",
|
1011 |
+
"format": "raw",
|
1012 |
+
"nbytes": 8388608,
|
1013 |
+
"byteOffset": 18876672
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"name": "model.layers.18.self_attn.o_proj.weight",
|
1017 |
+
"shape": [
|
1018 |
+
1024,
|
1019 |
+
2048
|
1020 |
+
],
|
1021 |
+
"dtype": "bfloat16",
|
1022 |
+
"format": "raw",
|
1023 |
+
"nbytes": 4194304,
|
1024 |
+
"byteOffset": 27265280
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"name": "model.layers.18.self_attn.q_norm.weight",
|
1028 |
+
"shape": [
|
1029 |
+
128
|
1030 |
+
],
|
1031 |
+
"dtype": "bfloat16",
|
1032 |
+
"format": "raw",
|
1033 |
+
"nbytes": 256,
|
1034 |
+
"byteOffset": 31459584
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"name": "model.layers.19.input_layernorm.weight",
|
1038 |
+
"shape": [
|
1039 |
+
1024
|
1040 |
+
],
|
1041 |
+
"dtype": "bfloat16",
|
1042 |
+
"format": "raw",
|
1043 |
+
"nbytes": 2048,
|
1044 |
+
"byteOffset": 31459840
|
1045 |
+
}
|
1046 |
+
],
|
1047 |
+
"md5sum": "961f8e1a308774dc0fd86312259d7c82"
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"dataPath": "params_shard_12.bin",
|
1051 |
+
"format": "raw-shard",
|
1052 |
+
"nbytes": 31461888,
|
1053 |
+
"records": [
|
1054 |
+
{
|
1055 |
+
"name": "model.layers.19.mlp.down_proj.weight",
|
1056 |
+
"shape": [
|
1057 |
+
1024,
|
1058 |
+
3072
|
1059 |
+
],
|
1060 |
+
"dtype": "bfloat16",
|
1061 |
+
"format": "raw",
|
1062 |
+
"nbytes": 6291456,
|
1063 |
+
"byteOffset": 0
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"name": "model.layers.19.mlp.gate_up_proj.weight",
|
1067 |
+
"shape": [
|
1068 |
+
6144,
|
1069 |
+
1024
|
1070 |
+
],
|
1071 |
+
"dtype": "bfloat16",
|
1072 |
+
"format": "raw",
|
1073 |
+
"nbytes": 12582912,
|
1074 |
+
"byteOffset": 6291456
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"name": "model.layers.19.post_attention_layernorm.weight",
|
1078 |
+
"shape": [
|
1079 |
+
1024
|
1080 |
+
],
|
1081 |
+
"dtype": "bfloat16",
|
1082 |
+
"format": "raw",
|
1083 |
+
"nbytes": 2048,
|
1084 |
+
"byteOffset": 18874368
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"name": "model.layers.19.self_attn.k_norm.weight",
|
1088 |
+
"shape": [
|
1089 |
+
128
|
1090 |
+
],
|
1091 |
+
"dtype": "bfloat16",
|
1092 |
+
"format": "raw",
|
1093 |
+
"nbytes": 256,
|
1094 |
+
"byteOffset": 18876416
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"name": "model.layers.19.self_attn.c_attn.weight",
|
1098 |
+
"shape": [
|
1099 |
+
4096,
|
1100 |
+
1024
|
1101 |
+
],
|
1102 |
+
"dtype": "bfloat16",
|
1103 |
+
"format": "raw",
|
1104 |
+
"nbytes": 8388608,
|
1105 |
+
"byteOffset": 18876672
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"name": "model.layers.19.self_attn.o_proj.weight",
|
1109 |
+
"shape": [
|
1110 |
+
1024,
|
1111 |
+
2048
|
1112 |
+
],
|
1113 |
+
"dtype": "bfloat16",
|
1114 |
+
"format": "raw",
|
1115 |
+
"nbytes": 4194304,
|
1116 |
+
"byteOffset": 27265280
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"name": "model.layers.19.self_attn.q_norm.weight",
|
1120 |
+
"shape": [
|
1121 |
+
128
|
1122 |
+
],
|
1123 |
+
"dtype": "bfloat16",
|
1124 |
+
"format": "raw",
|
1125 |
+
"nbytes": 256,
|
1126 |
+
"byteOffset": 31459584
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"name": "model.layers.2.input_layernorm.weight",
|
1130 |
+
"shape": [
|
1131 |
+
1024
|
1132 |
+
],
|
1133 |
+
"dtype": "bfloat16",
|
1134 |
+
"format": "raw",
|
1135 |
+
"nbytes": 2048,
|
1136 |
+
"byteOffset": 31459840
|
1137 |
+
}
|
1138 |
+
],
|
1139 |
+
"md5sum": "f17374b039b0e7a53080d4e8c61f1f16"
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"dataPath": "params_shard_13.bin",
|
1143 |
+
"format": "raw-shard",
|
1144 |
+
"nbytes": 31461888,
|
1145 |
+
"records": [
|
1146 |
+
{
|
1147 |
+
"name": "model.layers.2.mlp.down_proj.weight",
|
1148 |
+
"shape": [
|
1149 |
+
1024,
|
1150 |
+
3072
|
1151 |
+
],
|
1152 |
+
"dtype": "bfloat16",
|
1153 |
+
"format": "raw",
|
1154 |
+
"nbytes": 6291456,
|
1155 |
+
"byteOffset": 0
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"name": "model.layers.2.mlp.gate_up_proj.weight",
|
1159 |
+
"shape": [
|
1160 |
+
6144,
|
1161 |
+
1024
|
1162 |
+
],
|
1163 |
+
"dtype": "bfloat16",
|
1164 |
+
"format": "raw",
|
1165 |
+
"nbytes": 12582912,
|
1166 |
+
"byteOffset": 6291456
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
1170 |
+
"shape": [
|
1171 |
+
1024
|
1172 |
+
],
|
1173 |
+
"dtype": "bfloat16",
|
1174 |
+
"format": "raw",
|
1175 |
+
"nbytes": 2048,
|
1176 |
+
"byteOffset": 18874368
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"name": "model.layers.2.self_attn.k_norm.weight",
|
1180 |
+
"shape": [
|
1181 |
+
128
|
1182 |
+
],
|
1183 |
+
"dtype": "bfloat16",
|
1184 |
+
"format": "raw",
|
1185 |
+
"nbytes": 256,
|
1186 |
+
"byteOffset": 18876416
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"name": "model.layers.2.self_attn.c_attn.weight",
|
1190 |
+
"shape": [
|
1191 |
+
4096,
|
1192 |
+
1024
|
1193 |
+
],
|
1194 |
+
"dtype": "bfloat16",
|
1195 |
+
"format": "raw",
|
1196 |
+
"nbytes": 8388608,
|
1197 |
+
"byteOffset": 18876672
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"name": "model.layers.2.self_attn.o_proj.weight",
|
1201 |
+
"shape": [
|
1202 |
+
1024,
|
1203 |
+
2048
|
1204 |
+
],
|
1205 |
+
"dtype": "bfloat16",
|
1206 |
+
"format": "raw",
|
1207 |
+
"nbytes": 4194304,
|
1208 |
+
"byteOffset": 27265280
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"name": "model.layers.2.self_attn.q_norm.weight",
|
1212 |
+
"shape": [
|
1213 |
+
128
|
1214 |
+
],
|
1215 |
+
"dtype": "bfloat16",
|
1216 |
+
"format": "raw",
|
1217 |
+
"nbytes": 256,
|
1218 |
+
"byteOffset": 31459584
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"name": "model.layers.20.input_layernorm.weight",
|
1222 |
+
"shape": [
|
1223 |
+
1024
|
1224 |
+
],
|
1225 |
+
"dtype": "bfloat16",
|
1226 |
+
"format": "raw",
|
1227 |
+
"nbytes": 2048,
|
1228 |
+
"byteOffset": 31459840
|
1229 |
+
}
|
1230 |
+
],
|
1231 |
+
"md5sum": "7951ac8ebc3690aa9df718dfb599eb7b"
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"dataPath": "params_shard_14.bin",
|
1235 |
+
"format": "raw-shard",
|
1236 |
+
"nbytes": 31461888,
|
1237 |
+
"records": [
|
1238 |
+
{
|
1239 |
+
"name": "model.layers.20.mlp.down_proj.weight",
|
1240 |
+
"shape": [
|
1241 |
+
1024,
|
1242 |
+
3072
|
1243 |
+
],
|
1244 |
+
"dtype": "bfloat16",
|
1245 |
+
"format": "raw",
|
1246 |
+
"nbytes": 6291456,
|
1247 |
+
"byteOffset": 0
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"name": "model.layers.20.mlp.gate_up_proj.weight",
|
1251 |
+
"shape": [
|
1252 |
+
6144,
|
1253 |
+
1024
|
1254 |
+
],
|
1255 |
+
"dtype": "bfloat16",
|
1256 |
+
"format": "raw",
|
1257 |
+
"nbytes": 12582912,
|
1258 |
+
"byteOffset": 6291456
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"name": "model.layers.20.post_attention_layernorm.weight",
|
1262 |
+
"shape": [
|
1263 |
+
1024
|
1264 |
+
],
|
1265 |
+
"dtype": "bfloat16",
|
1266 |
+
"format": "raw",
|
1267 |
+
"nbytes": 2048,
|
1268 |
+
"byteOffset": 18874368
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"name": "model.layers.20.self_attn.k_norm.weight",
|
1272 |
+
"shape": [
|
1273 |
+
128
|
1274 |
+
],
|
1275 |
+
"dtype": "bfloat16",
|
1276 |
+
"format": "raw",
|
1277 |
+
"nbytes": 256,
|
1278 |
+
"byteOffset": 18876416
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"name": "model.layers.20.self_attn.c_attn.weight",
|
1282 |
+
"shape": [
|
1283 |
+
4096,
|
1284 |
+
1024
|
1285 |
+
],
|
1286 |
+
"dtype": "bfloat16",
|
1287 |
+
"format": "raw",
|
1288 |
+
"nbytes": 8388608,
|
1289 |
+
"byteOffset": 18876672
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"name": "model.layers.20.self_attn.o_proj.weight",
|
1293 |
+
"shape": [
|
1294 |
+
1024,
|
1295 |
+
2048
|
1296 |
+
],
|
1297 |
+
"dtype": "bfloat16",
|
1298 |
+
"format": "raw",
|
1299 |
+
"nbytes": 4194304,
|
1300 |
+
"byteOffset": 27265280
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"name": "model.layers.20.self_attn.q_norm.weight",
|
1304 |
+
"shape": [
|
1305 |
+
128
|
1306 |
+
],
|
1307 |
+
"dtype": "bfloat16",
|
1308 |
+
"format": "raw",
|
1309 |
+
"nbytes": 256,
|
1310 |
+
"byteOffset": 31459584
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"name": "model.layers.21.input_layernorm.weight",
|
1314 |
+
"shape": [
|
1315 |
+
1024
|
1316 |
+
],
|
1317 |
+
"dtype": "bfloat16",
|
1318 |
+
"format": "raw",
|
1319 |
+
"nbytes": 2048,
|
1320 |
+
"byteOffset": 31459840
|
1321 |
+
}
|
1322 |
+
],
|
1323 |
+
"md5sum": "a17e66b0197f5f796edc26b7c0b60a79"
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"dataPath": "params_shard_15.bin",
|
1327 |
+
"format": "raw-shard",
|
1328 |
+
"nbytes": 31461888,
|
1329 |
+
"records": [
|
1330 |
+
{
|
1331 |
+
"name": "model.layers.21.mlp.down_proj.weight",
|
1332 |
+
"shape": [
|
1333 |
+
1024,
|
1334 |
+
3072
|
1335 |
+
],
|
1336 |
+
"dtype": "bfloat16",
|
1337 |
+
"format": "raw",
|
1338 |
+
"nbytes": 6291456,
|
1339 |
+
"byteOffset": 0
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"name": "model.layers.21.mlp.gate_up_proj.weight",
|
1343 |
+
"shape": [
|
1344 |
+
6144,
|
1345 |
+
1024
|
1346 |
+
],
|
1347 |
+
"dtype": "bfloat16",
|
1348 |
+
"format": "raw",
|
1349 |
+
"nbytes": 12582912,
|
1350 |
+
"byteOffset": 6291456
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"name": "model.layers.21.post_attention_layernorm.weight",
|
1354 |
+
"shape": [
|
1355 |
+
1024
|
1356 |
+
],
|
1357 |
+
"dtype": "bfloat16",
|
1358 |
+
"format": "raw",
|
1359 |
+
"nbytes": 2048,
|
1360 |
+
"byteOffset": 18874368
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"name": "model.layers.21.self_attn.k_norm.weight",
|
1364 |
+
"shape": [
|
1365 |
+
128
|
1366 |
+
],
|
1367 |
+
"dtype": "bfloat16",
|
1368 |
+
"format": "raw",
|
1369 |
+
"nbytes": 256,
|
1370 |
+
"byteOffset": 18876416
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"name": "model.layers.21.self_attn.c_attn.weight",
|
1374 |
+
"shape": [
|
1375 |
+
4096,
|
1376 |
+
1024
|
1377 |
+
],
|
1378 |
+
"dtype": "bfloat16",
|
1379 |
+
"format": "raw",
|
1380 |
+
"nbytes": 8388608,
|
1381 |
+
"byteOffset": 18876672
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"name": "model.layers.21.self_attn.o_proj.weight",
|
1385 |
+
"shape": [
|
1386 |
+
1024,
|
1387 |
+
2048
|
1388 |
+
],
|
1389 |
+
"dtype": "bfloat16",
|
1390 |
+
"format": "raw",
|
1391 |
+
"nbytes": 4194304,
|
1392 |
+
"byteOffset": 27265280
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"name": "model.layers.21.self_attn.q_norm.weight",
|
1396 |
+
"shape": [
|
1397 |
+
128
|
1398 |
+
],
|
1399 |
+
"dtype": "bfloat16",
|
1400 |
+
"format": "raw",
|
1401 |
+
"nbytes": 256,
|
1402 |
+
"byteOffset": 31459584
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"name": "model.layers.22.input_layernorm.weight",
|
1406 |
+
"shape": [
|
1407 |
+
1024
|
1408 |
+
],
|
1409 |
+
"dtype": "bfloat16",
|
1410 |
+
"format": "raw",
|
1411 |
+
"nbytes": 2048,
|
1412 |
+
"byteOffset": 31459840
|
1413 |
+
}
|
1414 |
+
],
|
1415 |
+
"md5sum": "29dc75f0a0de71a20a19dc04d6ec2fe8"
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"dataPath": "params_shard_16.bin",
|
1419 |
+
"format": "raw-shard",
|
1420 |
+
"nbytes": 31461888,
|
1421 |
+
"records": [
|
1422 |
+
{
|
1423 |
+
"name": "model.layers.22.mlp.down_proj.weight",
|
1424 |
+
"shape": [
|
1425 |
+
1024,
|
1426 |
+
3072
|
1427 |
+
],
|
1428 |
+
"dtype": "bfloat16",
|
1429 |
+
"format": "raw",
|
1430 |
+
"nbytes": 6291456,
|
1431 |
+
"byteOffset": 0
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"name": "model.layers.22.mlp.gate_up_proj.weight",
|
1435 |
+
"shape": [
|
1436 |
+
6144,
|
1437 |
+
1024
|
1438 |
+
],
|
1439 |
+
"dtype": "bfloat16",
|
1440 |
+
"format": "raw",
|
1441 |
+
"nbytes": 12582912,
|
1442 |
+
"byteOffset": 6291456
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"name": "model.layers.22.post_attention_layernorm.weight",
|
1446 |
+
"shape": [
|
1447 |
+
1024
|
1448 |
+
],
|
1449 |
+
"dtype": "bfloat16",
|
1450 |
+
"format": "raw",
|
1451 |
+
"nbytes": 2048,
|
1452 |
+
"byteOffset": 18874368
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"name": "model.layers.22.self_attn.k_norm.weight",
|
1456 |
+
"shape": [
|
1457 |
+
128
|
1458 |
+
],
|
1459 |
+
"dtype": "bfloat16",
|
1460 |
+
"format": "raw",
|
1461 |
+
"nbytes": 256,
|
1462 |
+
"byteOffset": 18876416
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"name": "model.layers.22.self_attn.c_attn.weight",
|
1466 |
+
"shape": [
|
1467 |
+
4096,
|
1468 |
+
1024
|
1469 |
+
],
|
1470 |
+
"dtype": "bfloat16",
|
1471 |
+
"format": "raw",
|
1472 |
+
"nbytes": 8388608,
|
1473 |
+
"byteOffset": 18876672
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"name": "model.layers.22.self_attn.o_proj.weight",
|
1477 |
+
"shape": [
|
1478 |
+
1024,
|
1479 |
+
2048
|
1480 |
+
],
|
1481 |
+
"dtype": "bfloat16",
|
1482 |
+
"format": "raw",
|
1483 |
+
"nbytes": 4194304,
|
1484 |
+
"byteOffset": 27265280
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"name": "model.layers.22.self_attn.q_norm.weight",
|
1488 |
+
"shape": [
|
1489 |
+
128
|
1490 |
+
],
|
1491 |
+
"dtype": "bfloat16",
|
1492 |
+
"format": "raw",
|
1493 |
+
"nbytes": 256,
|
1494 |
+
"byteOffset": 31459584
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"name": "model.layers.23.input_layernorm.weight",
|
1498 |
+
"shape": [
|
1499 |
+
1024
|
1500 |
+
],
|
1501 |
+
"dtype": "bfloat16",
|
1502 |
+
"format": "raw",
|
1503 |
+
"nbytes": 2048,
|
1504 |
+
"byteOffset": 31459840
|
1505 |
+
}
|
1506 |
+
],
|
1507 |
+
"md5sum": "77370b671251a8b0f10de8721da680eb"
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"dataPath": "params_shard_17.bin",
|
1511 |
+
"format": "raw-shard",
|
1512 |
+
"nbytes": 31461888,
|
1513 |
+
"records": [
|
1514 |
+
{
|
1515 |
+
"name": "model.layers.23.mlp.down_proj.weight",
|
1516 |
+
"shape": [
|
1517 |
+
1024,
|
1518 |
+
3072
|
1519 |
+
],
|
1520 |
+
"dtype": "bfloat16",
|
1521 |
+
"format": "raw",
|
1522 |
+
"nbytes": 6291456,
|
1523 |
+
"byteOffset": 0
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"name": "model.layers.23.mlp.gate_up_proj.weight",
|
1527 |
+
"shape": [
|
1528 |
+
6144,
|
1529 |
+
1024
|
1530 |
+
],
|
1531 |
+
"dtype": "bfloat16",
|
1532 |
+
"format": "raw",
|
1533 |
+
"nbytes": 12582912,
|
1534 |
+
"byteOffset": 6291456
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"name": "model.layers.23.post_attention_layernorm.weight",
|
1538 |
+
"shape": [
|
1539 |
+
1024
|
1540 |
+
],
|
1541 |
+
"dtype": "bfloat16",
|
1542 |
+
"format": "raw",
|
1543 |
+
"nbytes": 2048,
|
1544 |
+
"byteOffset": 18874368
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"name": "model.layers.23.self_attn.k_norm.weight",
|
1548 |
+
"shape": [
|
1549 |
+
128
|
1550 |
+
],
|
1551 |
+
"dtype": "bfloat16",
|
1552 |
+
"format": "raw",
|
1553 |
+
"nbytes": 256,
|
1554 |
+
"byteOffset": 18876416
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"name": "model.layers.23.self_attn.c_attn.weight",
|
1558 |
+
"shape": [
|
1559 |
+
4096,
|
1560 |
+
1024
|
1561 |
+
],
|
1562 |
+
"dtype": "bfloat16",
|
1563 |
+
"format": "raw",
|
1564 |
+
"nbytes": 8388608,
|
1565 |
+
"byteOffset": 18876672
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"name": "model.layers.23.self_attn.o_proj.weight",
|
1569 |
+
"shape": [
|
1570 |
+
1024,
|
1571 |
+
2048
|
1572 |
+
],
|
1573 |
+
"dtype": "bfloat16",
|
1574 |
+
"format": "raw",
|
1575 |
+
"nbytes": 4194304,
|
1576 |
+
"byteOffset": 27265280
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"name": "model.layers.23.self_attn.q_norm.weight",
|
1580 |
+
"shape": [
|
1581 |
+
128
|
1582 |
+
],
|
1583 |
+
"dtype": "bfloat16",
|
1584 |
+
"format": "raw",
|
1585 |
+
"nbytes": 256,
|
1586 |
+
"byteOffset": 31459584
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"name": "model.layers.24.input_layernorm.weight",
|
1590 |
+
"shape": [
|
1591 |
+
1024
|
1592 |
+
],
|
1593 |
+
"dtype": "bfloat16",
|
1594 |
+
"format": "raw",
|
1595 |
+
"nbytes": 2048,
|
1596 |
+
"byteOffset": 31459840
|
1597 |
+
}
|
1598 |
+
],
|
1599 |
+
"md5sum": "e1b3dd47fb933da1144e2d4ee03a6447"
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"dataPath": "params_shard_18.bin",
|
1603 |
+
"format": "raw-shard",
|
1604 |
+
"nbytes": 31461888,
|
1605 |
+
"records": [
|
1606 |
+
{
|
1607 |
+
"name": "model.layers.24.mlp.down_proj.weight",
|
1608 |
+
"shape": [
|
1609 |
+
1024,
|
1610 |
+
3072
|
1611 |
+
],
|
1612 |
+
"dtype": "bfloat16",
|
1613 |
+
"format": "raw",
|
1614 |
+
"nbytes": 6291456,
|
1615 |
+
"byteOffset": 0
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"name": "model.layers.24.mlp.gate_up_proj.weight",
|
1619 |
+
"shape": [
|
1620 |
+
6144,
|
1621 |
+
1024
|
1622 |
+
],
|
1623 |
+
"dtype": "bfloat16",
|
1624 |
+
"format": "raw",
|
1625 |
+
"nbytes": 12582912,
|
1626 |
+
"byteOffset": 6291456
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"name": "model.layers.24.post_attention_layernorm.weight",
|
1630 |
+
"shape": [
|
1631 |
+
1024
|
1632 |
+
],
|
1633 |
+
"dtype": "bfloat16",
|
1634 |
+
"format": "raw",
|
1635 |
+
"nbytes": 2048,
|
1636 |
+
"byteOffset": 18874368
|
1637 |
+
},
|
1638 |
+
{
|
1639 |
+
"name": "model.layers.24.self_attn.k_norm.weight",
|
1640 |
+
"shape": [
|
1641 |
+
128
|
1642 |
+
],
|
1643 |
+
"dtype": "bfloat16",
|
1644 |
+
"format": "raw",
|
1645 |
+
"nbytes": 256,
|
1646 |
+
"byteOffset": 18876416
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"name": "model.layers.24.self_attn.c_attn.weight",
|
1650 |
+
"shape": [
|
1651 |
+
4096,
|
1652 |
+
1024
|
1653 |
+
],
|
1654 |
+
"dtype": "bfloat16",
|
1655 |
+
"format": "raw",
|
1656 |
+
"nbytes": 8388608,
|
1657 |
+
"byteOffset": 18876672
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"name": "model.layers.24.self_attn.o_proj.weight",
|
1661 |
+
"shape": [
|
1662 |
+
1024,
|
1663 |
+
2048
|
1664 |
+
],
|
1665 |
+
"dtype": "bfloat16",
|
1666 |
+
"format": "raw",
|
1667 |
+
"nbytes": 4194304,
|
1668 |
+
"byteOffset": 27265280
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"name": "model.layers.24.self_attn.q_norm.weight",
|
1672 |
+
"shape": [
|
1673 |
+
128
|
1674 |
+
],
|
1675 |
+
"dtype": "bfloat16",
|
1676 |
+
"format": "raw",
|
1677 |
+
"nbytes": 256,
|
1678 |
+
"byteOffset": 31459584
|
1679 |
+
},
|
1680 |
+
{
|
1681 |
+
"name": "model.layers.25.input_layernorm.weight",
|
1682 |
+
"shape": [
|
1683 |
+
1024
|
1684 |
+
],
|
1685 |
+
"dtype": "bfloat16",
|
1686 |
+
"format": "raw",
|
1687 |
+
"nbytes": 2048,
|
1688 |
+
"byteOffset": 31459840
|
1689 |
+
}
|
1690 |
+
],
|
1691 |
+
"md5sum": "1d9f848a8eba2d142c9aa2d536969ecf"
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"dataPath": "params_shard_19.bin",
|
1695 |
+
"format": "raw-shard",
|
1696 |
+
"nbytes": 31461888,
|
1697 |
+
"records": [
|
1698 |
+
{
|
1699 |
+
"name": "model.layers.25.mlp.down_proj.weight",
|
1700 |
+
"shape": [
|
1701 |
+
1024,
|
1702 |
+
3072
|
1703 |
+
],
|
1704 |
+
"dtype": "bfloat16",
|
1705 |
+
"format": "raw",
|
1706 |
+
"nbytes": 6291456,
|
1707 |
+
"byteOffset": 0
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"name": "model.layers.25.mlp.gate_up_proj.weight",
|
1711 |
+
"shape": [
|
1712 |
+
6144,
|
1713 |
+
1024
|
1714 |
+
],
|
1715 |
+
"dtype": "bfloat16",
|
1716 |
+
"format": "raw",
|
1717 |
+
"nbytes": 12582912,
|
1718 |
+
"byteOffset": 6291456
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"name": "model.layers.25.post_attention_layernorm.weight",
|
1722 |
+
"shape": [
|
1723 |
+
1024
|
1724 |
+
],
|
1725 |
+
"dtype": "bfloat16",
|
1726 |
+
"format": "raw",
|
1727 |
+
"nbytes": 2048,
|
1728 |
+
"byteOffset": 18874368
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"name": "model.layers.25.self_attn.k_norm.weight",
|
1732 |
+
"shape": [
|
1733 |
+
128
|
1734 |
+
],
|
1735 |
+
"dtype": "bfloat16",
|
1736 |
+
"format": "raw",
|
1737 |
+
"nbytes": 256,
|
1738 |
+
"byteOffset": 18876416
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"name": "model.layers.25.self_attn.c_attn.weight",
|
1742 |
+
"shape": [
|
1743 |
+
4096,
|
1744 |
+
1024
|
1745 |
+
],
|
1746 |
+
"dtype": "bfloat16",
|
1747 |
+
"format": "raw",
|
1748 |
+
"nbytes": 8388608,
|
1749 |
+
"byteOffset": 18876672
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"name": "model.layers.25.self_attn.o_proj.weight",
|
1753 |
+
"shape": [
|
1754 |
+
1024,
|
1755 |
+
2048
|
1756 |
+
],
|
1757 |
+
"dtype": "bfloat16",
|
1758 |
+
"format": "raw",
|
1759 |
+
"nbytes": 4194304,
|
1760 |
+
"byteOffset": 27265280
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"name": "model.layers.25.self_attn.q_norm.weight",
|
1764 |
+
"shape": [
|
1765 |
+
128
|
1766 |
+
],
|
1767 |
+
"dtype": "bfloat16",
|
1768 |
+
"format": "raw",
|
1769 |
+
"nbytes": 256,
|
1770 |
+
"byteOffset": 31459584
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"name": "model.layers.26.input_layernorm.weight",
|
1774 |
+
"shape": [
|
1775 |
+
1024
|
1776 |
+
],
|
1777 |
+
"dtype": "bfloat16",
|
1778 |
+
"format": "raw",
|
1779 |
+
"nbytes": 2048,
|
1780 |
+
"byteOffset": 31459840
|
1781 |
+
}
|
1782 |
+
],
|
1783 |
+
"md5sum": "e6125aaacc98c10d3e7702aa6bdb39d8"
|
1784 |
+
},
|
1785 |
+
{
|
1786 |
+
"dataPath": "params_shard_20.bin",
|
1787 |
+
"format": "raw-shard",
|
1788 |
+
"nbytes": 31461888,
|
1789 |
+
"records": [
|
1790 |
+
{
|
1791 |
+
"name": "model.layers.26.mlp.down_proj.weight",
|
1792 |
+
"shape": [
|
1793 |
+
1024,
|
1794 |
+
3072
|
1795 |
+
],
|
1796 |
+
"dtype": "bfloat16",
|
1797 |
+
"format": "raw",
|
1798 |
+
"nbytes": 6291456,
|
1799 |
+
"byteOffset": 0
|
1800 |
+
},
|
1801 |
+
{
|
1802 |
+
"name": "model.layers.26.mlp.gate_up_proj.weight",
|
1803 |
+
"shape": [
|
1804 |
+
6144,
|
1805 |
+
1024
|
1806 |
+
],
|
1807 |
+
"dtype": "bfloat16",
|
1808 |
+
"format": "raw",
|
1809 |
+
"nbytes": 12582912,
|
1810 |
+
"byteOffset": 6291456
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"name": "model.layers.26.post_attention_layernorm.weight",
|
1814 |
+
"shape": [
|
1815 |
+
1024
|
1816 |
+
],
|
1817 |
+
"dtype": "bfloat16",
|
1818 |
+
"format": "raw",
|
1819 |
+
"nbytes": 2048,
|
1820 |
+
"byteOffset": 18874368
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"name": "model.layers.26.self_attn.k_norm.weight",
|
1824 |
+
"shape": [
|
1825 |
+
128
|
1826 |
+
],
|
1827 |
+
"dtype": "bfloat16",
|
1828 |
+
"format": "raw",
|
1829 |
+
"nbytes": 256,
|
1830 |
+
"byteOffset": 18876416
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"name": "model.layers.26.self_attn.c_attn.weight",
|
1834 |
+
"shape": [
|
1835 |
+
4096,
|
1836 |
+
1024
|
1837 |
+
],
|
1838 |
+
"dtype": "bfloat16",
|
1839 |
+
"format": "raw",
|
1840 |
+
"nbytes": 8388608,
|
1841 |
+
"byteOffset": 18876672
|
1842 |
+
},
|
1843 |
+
{
|
1844 |
+
"name": "model.layers.26.self_attn.o_proj.weight",
|
1845 |
+
"shape": [
|
1846 |
+
1024,
|
1847 |
+
2048
|
1848 |
+
],
|
1849 |
+
"dtype": "bfloat16",
|
1850 |
+
"format": "raw",
|
1851 |
+
"nbytes": 4194304,
|
1852 |
+
"byteOffset": 27265280
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"name": "model.layers.26.self_attn.q_norm.weight",
|
1856 |
+
"shape": [
|
1857 |
+
128
|
1858 |
+
],
|
1859 |
+
"dtype": "bfloat16",
|
1860 |
+
"format": "raw",
|
1861 |
+
"nbytes": 256,
|
1862 |
+
"byteOffset": 31459584
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"name": "model.layers.27.input_layernorm.weight",
|
1866 |
+
"shape": [
|
1867 |
+
1024
|
1868 |
+
],
|
1869 |
+
"dtype": "bfloat16",
|
1870 |
+
"format": "raw",
|
1871 |
+
"nbytes": 2048,
|
1872 |
+
"byteOffset": 31459840
|
1873 |
+
}
|
1874 |
+
],
|
1875 |
+
"md5sum": "9d135333707ef2f4acb7dd7cf9326f25"
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"dataPath": "params_shard_21.bin",
|
1879 |
+
"format": "raw-shard",
|
1880 |
+
"nbytes": 31461888,
|
1881 |
+
"records": [
|
1882 |
+
{
|
1883 |
+
"name": "model.layers.27.mlp.down_proj.weight",
|
1884 |
+
"shape": [
|
1885 |
+
1024,
|
1886 |
+
3072
|
1887 |
+
],
|
1888 |
+
"dtype": "bfloat16",
|
1889 |
+
"format": "raw",
|
1890 |
+
"nbytes": 6291456,
|
1891 |
+
"byteOffset": 0
|
1892 |
+
},
|
1893 |
+
{
|
1894 |
+
"name": "model.layers.27.mlp.gate_up_proj.weight",
|
1895 |
+
"shape": [
|
1896 |
+
6144,
|
1897 |
+
1024
|
1898 |
+
],
|
1899 |
+
"dtype": "bfloat16",
|
1900 |
+
"format": "raw",
|
1901 |
+
"nbytes": 12582912,
|
1902 |
+
"byteOffset": 6291456
|
1903 |
+
},
|
1904 |
+
{
|
1905 |
+
"name": "model.layers.27.post_attention_layernorm.weight",
|
1906 |
+
"shape": [
|
1907 |
+
1024
|
1908 |
+
],
|
1909 |
+
"dtype": "bfloat16",
|
1910 |
+
"format": "raw",
|
1911 |
+
"nbytes": 2048,
|
1912 |
+
"byteOffset": 18874368
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"name": "model.layers.27.self_attn.k_norm.weight",
|
1916 |
+
"shape": [
|
1917 |
+
128
|
1918 |
+
],
|
1919 |
+
"dtype": "bfloat16",
|
1920 |
+
"format": "raw",
|
1921 |
+
"nbytes": 256,
|
1922 |
+
"byteOffset": 18876416
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"name": "model.layers.27.self_attn.c_attn.weight",
|
1926 |
+
"shape": [
|
1927 |
+
4096,
|
1928 |
+
1024
|
1929 |
+
],
|
1930 |
+
"dtype": "bfloat16",
|
1931 |
+
"format": "raw",
|
1932 |
+
"nbytes": 8388608,
|
1933 |
+
"byteOffset": 18876672
|
1934 |
+
},
|
1935 |
+
{
|
1936 |
+
"name": "model.layers.27.self_attn.o_proj.weight",
|
1937 |
+
"shape": [
|
1938 |
+
1024,
|
1939 |
+
2048
|
1940 |
+
],
|
1941 |
+
"dtype": "bfloat16",
|
1942 |
+
"format": "raw",
|
1943 |
+
"nbytes": 4194304,
|
1944 |
+
"byteOffset": 27265280
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"name": "model.layers.27.self_attn.q_norm.weight",
|
1948 |
+
"shape": [
|
1949 |
+
128
|
1950 |
+
],
|
1951 |
+
"dtype": "bfloat16",
|
1952 |
+
"format": "raw",
|
1953 |
+
"nbytes": 256,
|
1954 |
+
"byteOffset": 31459584
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"name": "model.layers.3.input_layernorm.weight",
|
1958 |
+
"shape": [
|
1959 |
+
1024
|
1960 |
+
],
|
1961 |
+
"dtype": "bfloat16",
|
1962 |
+
"format": "raw",
|
1963 |
+
"nbytes": 2048,
|
1964 |
+
"byteOffset": 31459840
|
1965 |
+
}
|
1966 |
+
],
|
1967 |
+
"md5sum": "e07ec46dc1988b87491a60c6e922c02a"
|
1968 |
+
},
|
1969 |
+
{
|
1970 |
+
"dataPath": "params_shard_22.bin",
|
1971 |
+
"format": "raw-shard",
|
1972 |
+
"nbytes": 31461888,
|
1973 |
+
"records": [
|
1974 |
+
{
|
1975 |
+
"name": "model.layers.3.mlp.down_proj.weight",
|
1976 |
+
"shape": [
|
1977 |
+
1024,
|
1978 |
+
3072
|
1979 |
+
],
|
1980 |
+
"dtype": "bfloat16",
|
1981 |
+
"format": "raw",
|
1982 |
+
"nbytes": 6291456,
|
1983 |
+
"byteOffset": 0
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"name": "model.layers.3.mlp.gate_up_proj.weight",
|
1987 |
+
"shape": [
|
1988 |
+
6144,
|
1989 |
+
1024
|
1990 |
+
],
|
1991 |
+
"dtype": "bfloat16",
|
1992 |
+
"format": "raw",
|
1993 |
+
"nbytes": 12582912,
|
1994 |
+
"byteOffset": 6291456
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
1998 |
+
"shape": [
|
1999 |
+
1024
|
2000 |
+
],
|
2001 |
+
"dtype": "bfloat16",
|
2002 |
+
"format": "raw",
|
2003 |
+
"nbytes": 2048,
|
2004 |
+
"byteOffset": 18874368
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"name": "model.layers.3.self_attn.k_norm.weight",
|
2008 |
+
"shape": [
|
2009 |
+
128
|
2010 |
+
],
|
2011 |
+
"dtype": "bfloat16",
|
2012 |
+
"format": "raw",
|
2013 |
+
"nbytes": 256,
|
2014 |
+
"byteOffset": 18876416
|
2015 |
+
},
|
2016 |
+
{
|
2017 |
+
"name": "model.layers.3.self_attn.c_attn.weight",
|
2018 |
+
"shape": [
|
2019 |
+
4096,
|
2020 |
+
1024
|
2021 |
+
],
|
2022 |
+
"dtype": "bfloat16",
|
2023 |
+
"format": "raw",
|
2024 |
+
"nbytes": 8388608,
|
2025 |
+
"byteOffset": 18876672
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"name": "model.layers.3.self_attn.o_proj.weight",
|
2029 |
+
"shape": [
|
2030 |
+
1024,
|
2031 |
+
2048
|
2032 |
+
],
|
2033 |
+
"dtype": "bfloat16",
|
2034 |
+
"format": "raw",
|
2035 |
+
"nbytes": 4194304,
|
2036 |
+
"byteOffset": 27265280
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"name": "model.layers.3.self_attn.q_norm.weight",
|
2040 |
+
"shape": [
|
2041 |
+
128
|
2042 |
+
],
|
2043 |
+
"dtype": "bfloat16",
|
2044 |
+
"format": "raw",
|
2045 |
+
"nbytes": 256,
|
2046 |
+
"byteOffset": 31459584
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"name": "model.layers.4.input_layernorm.weight",
|
2050 |
+
"shape": [
|
2051 |
+
1024
|
2052 |
+
],
|
2053 |
+
"dtype": "bfloat16",
|
2054 |
+
"format": "raw",
|
2055 |
+
"nbytes": 2048,
|
2056 |
+
"byteOffset": 31459840
|
2057 |
+
}
|
2058 |
+
],
|
2059 |
+
"md5sum": "f0b4915b859259222e9787ee1e7b354d"
|
2060 |
+
},
|
2061 |
+
{
|
2062 |
+
"dataPath": "params_shard_23.bin",
|
2063 |
+
"format": "raw-shard",
|
2064 |
+
"nbytes": 31461888,
|
2065 |
+
"records": [
|
2066 |
+
{
|
2067 |
+
"name": "model.layers.4.mlp.down_proj.weight",
|
2068 |
+
"shape": [
|
2069 |
+
1024,
|
2070 |
+
3072
|
2071 |
+
],
|
2072 |
+
"dtype": "bfloat16",
|
2073 |
+
"format": "raw",
|
2074 |
+
"nbytes": 6291456,
|
2075 |
+
"byteOffset": 0
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"name": "model.layers.4.mlp.gate_up_proj.weight",
|
2079 |
+
"shape": [
|
2080 |
+
6144,
|
2081 |
+
1024
|
2082 |
+
],
|
2083 |
+
"dtype": "bfloat16",
|
2084 |
+
"format": "raw",
|
2085 |
+
"nbytes": 12582912,
|
2086 |
+
"byteOffset": 6291456
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
2090 |
+
"shape": [
|
2091 |
+
1024
|
2092 |
+
],
|
2093 |
+
"dtype": "bfloat16",
|
2094 |
+
"format": "raw",
|
2095 |
+
"nbytes": 2048,
|
2096 |
+
"byteOffset": 18874368
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"name": "model.layers.4.self_attn.k_norm.weight",
|
2100 |
+
"shape": [
|
2101 |
+
128
|
2102 |
+
],
|
2103 |
+
"dtype": "bfloat16",
|
2104 |
+
"format": "raw",
|
2105 |
+
"nbytes": 256,
|
2106 |
+
"byteOffset": 18876416
|
2107 |
+
},
|
2108 |
+
{
|
2109 |
+
"name": "model.layers.4.self_attn.c_attn.weight",
|
2110 |
+
"shape": [
|
2111 |
+
4096,
|
2112 |
+
1024
|
2113 |
+
],
|
2114 |
+
"dtype": "bfloat16",
|
2115 |
+
"format": "raw",
|
2116 |
+
"nbytes": 8388608,
|
2117 |
+
"byteOffset": 18876672
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"name": "model.layers.4.self_attn.o_proj.weight",
|
2121 |
+
"shape": [
|
2122 |
+
1024,
|
2123 |
+
2048
|
2124 |
+
],
|
2125 |
+
"dtype": "bfloat16",
|
2126 |
+
"format": "raw",
|
2127 |
+
"nbytes": 4194304,
|
2128 |
+
"byteOffset": 27265280
|
2129 |
+
},
|
2130 |
+
{
|
2131 |
+
"name": "model.layers.4.self_attn.q_norm.weight",
|
2132 |
+
"shape": [
|
2133 |
+
128
|
2134 |
+
],
|
2135 |
+
"dtype": "bfloat16",
|
2136 |
+
"format": "raw",
|
2137 |
+
"nbytes": 256,
|
2138 |
+
"byteOffset": 31459584
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"name": "model.layers.5.input_layernorm.weight",
|
2142 |
+
"shape": [
|
2143 |
+
1024
|
2144 |
+
],
|
2145 |
+
"dtype": "bfloat16",
|
2146 |
+
"format": "raw",
|
2147 |
+
"nbytes": 2048,
|
2148 |
+
"byteOffset": 31459840
|
2149 |
+
}
|
2150 |
+
],
|
2151 |
+
"md5sum": "890c68f7289867143b40975439f97c02"
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"dataPath": "params_shard_24.bin",
|
2155 |
+
"format": "raw-shard",
|
2156 |
+
"nbytes": 31461888,
|
2157 |
+
"records": [
|
2158 |
+
{
|
2159 |
+
"name": "model.layers.5.mlp.down_proj.weight",
|
2160 |
+
"shape": [
|
2161 |
+
1024,
|
2162 |
+
3072
|
2163 |
+
],
|
2164 |
+
"dtype": "bfloat16",
|
2165 |
+
"format": "raw",
|
2166 |
+
"nbytes": 6291456,
|
2167 |
+
"byteOffset": 0
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"name": "model.layers.5.mlp.gate_up_proj.weight",
|
2171 |
+
"shape": [
|
2172 |
+
6144,
|
2173 |
+
1024
|
2174 |
+
],
|
2175 |
+
"dtype": "bfloat16",
|
2176 |
+
"format": "raw",
|
2177 |
+
"nbytes": 12582912,
|
2178 |
+
"byteOffset": 6291456
|
2179 |
+
},
|
2180 |
+
{
|
2181 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
2182 |
+
"shape": [
|
2183 |
+
1024
|
2184 |
+
],
|
2185 |
+
"dtype": "bfloat16",
|
2186 |
+
"format": "raw",
|
2187 |
+
"nbytes": 2048,
|
2188 |
+
"byteOffset": 18874368
|
2189 |
+
},
|
2190 |
+
{
|
2191 |
+
"name": "model.layers.5.self_attn.k_norm.weight",
|
2192 |
+
"shape": [
|
2193 |
+
128
|
2194 |
+
],
|
2195 |
+
"dtype": "bfloat16",
|
2196 |
+
"format": "raw",
|
2197 |
+
"nbytes": 256,
|
2198 |
+
"byteOffset": 18876416
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"name": "model.layers.5.self_attn.c_attn.weight",
|
2202 |
+
"shape": [
|
2203 |
+
4096,
|
2204 |
+
1024
|
2205 |
+
],
|
2206 |
+
"dtype": "bfloat16",
|
2207 |
+
"format": "raw",
|
2208 |
+
"nbytes": 8388608,
|
2209 |
+
"byteOffset": 18876672
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"name": "model.layers.5.self_attn.o_proj.weight",
|
2213 |
+
"shape": [
|
2214 |
+
1024,
|
2215 |
+
2048
|
2216 |
+
],
|
2217 |
+
"dtype": "bfloat16",
|
2218 |
+
"format": "raw",
|
2219 |
+
"nbytes": 4194304,
|
2220 |
+
"byteOffset": 27265280
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"name": "model.layers.5.self_attn.q_norm.weight",
|
2224 |
+
"shape": [
|
2225 |
+
128
|
2226 |
+
],
|
2227 |
+
"dtype": "bfloat16",
|
2228 |
+
"format": "raw",
|
2229 |
+
"nbytes": 256,
|
2230 |
+
"byteOffset": 31459584
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"name": "model.layers.6.input_layernorm.weight",
|
2234 |
+
"shape": [
|
2235 |
+
1024
|
2236 |
+
],
|
2237 |
+
"dtype": "bfloat16",
|
2238 |
+
"format": "raw",
|
2239 |
+
"nbytes": 2048,
|
2240 |
+
"byteOffset": 31459840
|
2241 |
+
}
|
2242 |
+
],
|
2243 |
+
"md5sum": "4a2e6abf9a0ac27fed499bb02f61047b"
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"dataPath": "params_shard_25.bin",
|
2247 |
+
"format": "raw-shard",
|
2248 |
+
"nbytes": 31461888,
|
2249 |
+
"records": [
|
2250 |
+
{
|
2251 |
+
"name": "model.layers.6.mlp.down_proj.weight",
|
2252 |
+
"shape": [
|
2253 |
+
1024,
|
2254 |
+
3072
|
2255 |
+
],
|
2256 |
+
"dtype": "bfloat16",
|
2257 |
+
"format": "raw",
|
2258 |
+
"nbytes": 6291456,
|
2259 |
+
"byteOffset": 0
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"name": "model.layers.6.mlp.gate_up_proj.weight",
|
2263 |
+
"shape": [
|
2264 |
+
6144,
|
2265 |
+
1024
|
2266 |
+
],
|
2267 |
+
"dtype": "bfloat16",
|
2268 |
+
"format": "raw",
|
2269 |
+
"nbytes": 12582912,
|
2270 |
+
"byteOffset": 6291456
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
2274 |
+
"shape": [
|
2275 |
+
1024
|
2276 |
+
],
|
2277 |
+
"dtype": "bfloat16",
|
2278 |
+
"format": "raw",
|
2279 |
+
"nbytes": 2048,
|
2280 |
+
"byteOffset": 18874368
|
2281 |
+
},
|
2282 |
+
{
|
2283 |
+
"name": "model.layers.6.self_attn.k_norm.weight",
|
2284 |
+
"shape": [
|
2285 |
+
128
|
2286 |
+
],
|
2287 |
+
"dtype": "bfloat16",
|
2288 |
+
"format": "raw",
|
2289 |
+
"nbytes": 256,
|
2290 |
+
"byteOffset": 18876416
|
2291 |
+
},
|
2292 |
+
{
|
2293 |
+
"name": "model.layers.6.self_attn.c_attn.weight",
|
2294 |
+
"shape": [
|
2295 |
+
4096,
|
2296 |
+
1024
|
2297 |
+
],
|
2298 |
+
"dtype": "bfloat16",
|
2299 |
+
"format": "raw",
|
2300 |
+
"nbytes": 8388608,
|
2301 |
+
"byteOffset": 18876672
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"name": "model.layers.6.self_attn.o_proj.weight",
|
2305 |
+
"shape": [
|
2306 |
+
1024,
|
2307 |
+
2048
|
2308 |
+
],
|
2309 |
+
"dtype": "bfloat16",
|
2310 |
+
"format": "raw",
|
2311 |
+
"nbytes": 4194304,
|
2312 |
+
"byteOffset": 27265280
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"name": "model.layers.6.self_attn.q_norm.weight",
|
2316 |
+
"shape": [
|
2317 |
+
128
|
2318 |
+
],
|
2319 |
+
"dtype": "bfloat16",
|
2320 |
+
"format": "raw",
|
2321 |
+
"nbytes": 256,
|
2322 |
+
"byteOffset": 31459584
|
2323 |
+
},
|
2324 |
+
{
|
2325 |
+
"name": "model.layers.7.input_layernorm.weight",
|
2326 |
+
"shape": [
|
2327 |
+
1024
|
2328 |
+
],
|
2329 |
+
"dtype": "bfloat16",
|
2330 |
+
"format": "raw",
|
2331 |
+
"nbytes": 2048,
|
2332 |
+
"byteOffset": 31459840
|
2333 |
+
}
|
2334 |
+
],
|
2335 |
+
"md5sum": "bbf21bdcb33c7b1dfaf7279672693cc2"
|
2336 |
+
},
|
2337 |
+
{
|
2338 |
+
"dataPath": "params_shard_26.bin",
|
2339 |
+
"format": "raw-shard",
|
2340 |
+
"nbytes": 31461888,
|
2341 |
+
"records": [
|
2342 |
+
{
|
2343 |
+
"name": "model.layers.7.mlp.down_proj.weight",
|
2344 |
+
"shape": [
|
2345 |
+
1024,
|
2346 |
+
3072
|
2347 |
+
],
|
2348 |
+
"dtype": "bfloat16",
|
2349 |
+
"format": "raw",
|
2350 |
+
"nbytes": 6291456,
|
2351 |
+
"byteOffset": 0
|
2352 |
+
},
|
2353 |
+
{
|
2354 |
+
"name": "model.layers.7.mlp.gate_up_proj.weight",
|
2355 |
+
"shape": [
|
2356 |
+
6144,
|
2357 |
+
1024
|
2358 |
+
],
|
2359 |
+
"dtype": "bfloat16",
|
2360 |
+
"format": "raw",
|
2361 |
+
"nbytes": 12582912,
|
2362 |
+
"byteOffset": 6291456
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
2366 |
+
"shape": [
|
2367 |
+
1024
|
2368 |
+
],
|
2369 |
+
"dtype": "bfloat16",
|
2370 |
+
"format": "raw",
|
2371 |
+
"nbytes": 2048,
|
2372 |
+
"byteOffset": 18874368
|
2373 |
+
},
|
2374 |
+
{
|
2375 |
+
"name": "model.layers.7.self_attn.k_norm.weight",
|
2376 |
+
"shape": [
|
2377 |
+
128
|
2378 |
+
],
|
2379 |
+
"dtype": "bfloat16",
|
2380 |
+
"format": "raw",
|
2381 |
+
"nbytes": 256,
|
2382 |
+
"byteOffset": 18876416
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"name": "model.layers.7.self_attn.c_attn.weight",
|
2386 |
+
"shape": [
|
2387 |
+
4096,
|
2388 |
+
1024
|
2389 |
+
],
|
2390 |
+
"dtype": "bfloat16",
|
2391 |
+
"format": "raw",
|
2392 |
+
"nbytes": 8388608,
|
2393 |
+
"byteOffset": 18876672
|
2394 |
+
},
|
2395 |
+
{
|
2396 |
+
"name": "model.layers.7.self_attn.o_proj.weight",
|
2397 |
+
"shape": [
|
2398 |
+
1024,
|
2399 |
+
2048
|
2400 |
+
],
|
2401 |
+
"dtype": "bfloat16",
|
2402 |
+
"format": "raw",
|
2403 |
+
"nbytes": 4194304,
|
2404 |
+
"byteOffset": 27265280
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"name": "model.layers.7.self_attn.q_norm.weight",
|
2408 |
+
"shape": [
|
2409 |
+
128
|
2410 |
+
],
|
2411 |
+
"dtype": "bfloat16",
|
2412 |
+
"format": "raw",
|
2413 |
+
"nbytes": 256,
|
2414 |
+
"byteOffset": 31459584
|
2415 |
+
},
|
2416 |
+
{
|
2417 |
+
"name": "model.layers.8.input_layernorm.weight",
|
2418 |
+
"shape": [
|
2419 |
+
1024
|
2420 |
+
],
|
2421 |
+
"dtype": "bfloat16",
|
2422 |
+
"format": "raw",
|
2423 |
+
"nbytes": 2048,
|
2424 |
+
"byteOffset": 31459840
|
2425 |
+
}
|
2426 |
+
],
|
2427 |
+
"md5sum": "d0db88ea1fdab01e768d9ee5a4cc24e1"
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"dataPath": "params_shard_27.bin",
|
2431 |
+
"format": "raw-shard",
|
2432 |
+
"nbytes": 31461888,
|
2433 |
+
"records": [
|
2434 |
+
{
|
2435 |
+
"name": "model.layers.8.mlp.down_proj.weight",
|
2436 |
+
"shape": [
|
2437 |
+
1024,
|
2438 |
+
3072
|
2439 |
+
],
|
2440 |
+
"dtype": "bfloat16",
|
2441 |
+
"format": "raw",
|
2442 |
+
"nbytes": 6291456,
|
2443 |
+
"byteOffset": 0
|
2444 |
+
},
|
2445 |
+
{
|
2446 |
+
"name": "model.layers.8.mlp.gate_up_proj.weight",
|
2447 |
+
"shape": [
|
2448 |
+
6144,
|
2449 |
+
1024
|
2450 |
+
],
|
2451 |
+
"dtype": "bfloat16",
|
2452 |
+
"format": "raw",
|
2453 |
+
"nbytes": 12582912,
|
2454 |
+
"byteOffset": 6291456
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
2458 |
+
"shape": [
|
2459 |
+
1024
|
2460 |
+
],
|
2461 |
+
"dtype": "bfloat16",
|
2462 |
+
"format": "raw",
|
2463 |
+
"nbytes": 2048,
|
2464 |
+
"byteOffset": 18874368
|
2465 |
+
},
|
2466 |
+
{
|
2467 |
+
"name": "model.layers.8.self_attn.k_norm.weight",
|
2468 |
+
"shape": [
|
2469 |
+
128
|
2470 |
+
],
|
2471 |
+
"dtype": "bfloat16",
|
2472 |
+
"format": "raw",
|
2473 |
+
"nbytes": 256,
|
2474 |
+
"byteOffset": 18876416
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"name": "model.layers.8.self_attn.c_attn.weight",
|
2478 |
+
"shape": [
|
2479 |
+
4096,
|
2480 |
+
1024
|
2481 |
+
],
|
2482 |
+
"dtype": "bfloat16",
|
2483 |
+
"format": "raw",
|
2484 |
+
"nbytes": 8388608,
|
2485 |
+
"byteOffset": 18876672
|
2486 |
+
},
|
2487 |
+
{
|
2488 |
+
"name": "model.layers.8.self_attn.o_proj.weight",
|
2489 |
+
"shape": [
|
2490 |
+
1024,
|
2491 |
+
2048
|
2492 |
+
],
|
2493 |
+
"dtype": "bfloat16",
|
2494 |
+
"format": "raw",
|
2495 |
+
"nbytes": 4194304,
|
2496 |
+
"byteOffset": 27265280
|
2497 |
+
},
|
2498 |
+
{
|
2499 |
+
"name": "model.layers.8.self_attn.q_norm.weight",
|
2500 |
+
"shape": [
|
2501 |
+
128
|
2502 |
+
],
|
2503 |
+
"dtype": "bfloat16",
|
2504 |
+
"format": "raw",
|
2505 |
+
"nbytes": 256,
|
2506 |
+
"byteOffset": 31459584
|
2507 |
+
},
|
2508 |
+
{
|
2509 |
+
"name": "model.layers.9.input_layernorm.weight",
|
2510 |
+
"shape": [
|
2511 |
+
1024
|
2512 |
+
],
|
2513 |
+
"dtype": "bfloat16",
|
2514 |
+
"format": "raw",
|
2515 |
+
"nbytes": 2048,
|
2516 |
+
"byteOffset": 31459840
|
2517 |
+
}
|
2518 |
+
],
|
2519 |
+
"md5sum": "3a05a1acf71722e4ad3b000b324a8649"
|
2520 |
+
},
|
2521 |
+
{
|
2522 |
+
"dataPath": "params_shard_28.bin",
|
2523 |
+
"format": "raw-shard",
|
2524 |
+
"nbytes": 31461888,
|
2525 |
+
"records": [
|
2526 |
+
{
|
2527 |
+
"name": "model.layers.9.mlp.down_proj.weight",
|
2528 |
+
"shape": [
|
2529 |
+
1024,
|
2530 |
+
3072
|
2531 |
+
],
|
2532 |
+
"dtype": "bfloat16",
|
2533 |
+
"format": "raw",
|
2534 |
+
"nbytes": 6291456,
|
2535 |
+
"byteOffset": 0
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"name": "model.layers.9.mlp.gate_up_proj.weight",
|
2539 |
+
"shape": [
|
2540 |
+
6144,
|
2541 |
+
1024
|
2542 |
+
],
|
2543 |
+
"dtype": "bfloat16",
|
2544 |
+
"format": "raw",
|
2545 |
+
"nbytes": 12582912,
|
2546 |
+
"byteOffset": 6291456
|
2547 |
+
},
|
2548 |
+
{
|
2549 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
2550 |
+
"shape": [
|
2551 |
+
1024
|
2552 |
+
],
|
2553 |
+
"dtype": "bfloat16",
|
2554 |
+
"format": "raw",
|
2555 |
+
"nbytes": 2048,
|
2556 |
+
"byteOffset": 18874368
|
2557 |
+
},
|
2558 |
+
{
|
2559 |
+
"name": "model.layers.9.self_attn.k_norm.weight",
|
2560 |
+
"shape": [
|
2561 |
+
128
|
2562 |
+
],
|
2563 |
+
"dtype": "bfloat16",
|
2564 |
+
"format": "raw",
|
2565 |
+
"nbytes": 256,
|
2566 |
+
"byteOffset": 18876416
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"name": "model.layers.9.self_attn.c_attn.weight",
|
2570 |
+
"shape": [
|
2571 |
+
4096,
|
2572 |
+
1024
|
2573 |
+
],
|
2574 |
+
"dtype": "bfloat16",
|
2575 |
+
"format": "raw",
|
2576 |
+
"nbytes": 8388608,
|
2577 |
+
"byteOffset": 18876672
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"name": "model.layers.9.self_attn.o_proj.weight",
|
2581 |
+
"shape": [
|
2582 |
+
1024,
|
2583 |
+
2048
|
2584 |
+
],
|
2585 |
+
"dtype": "bfloat16",
|
2586 |
+
"format": "raw",
|
2587 |
+
"nbytes": 4194304,
|
2588 |
+
"byteOffset": 27265280
|
2589 |
+
},
|
2590 |
+
{
|
2591 |
+
"name": "model.layers.9.self_attn.q_norm.weight",
|
2592 |
+
"shape": [
|
2593 |
+
128
|
2594 |
+
],
|
2595 |
+
"dtype": "bfloat16",
|
2596 |
+
"format": "raw",
|
2597 |
+
"nbytes": 256,
|
2598 |
+
"byteOffset": 31459584
|
2599 |
+
},
|
2600 |
+
{
|
2601 |
+
"name": "model.norm.weight",
|
2602 |
+
"shape": [
|
2603 |
+
1024
|
2604 |
+
],
|
2605 |
+
"dtype": "bfloat16",
|
2606 |
+
"format": "raw",
|
2607 |
+
"nbytes": 2048,
|
2608 |
+
"byteOffset": 31459840
|
2609 |
+
}
|
2610 |
+
],
|
2611 |
+
"md5sum": "195d11d45fdbd6e214234ed298ed0684"
|
2612 |
+
}
|
2613 |
+
]
|
2614 |
+
}
|
ndarray-cache.json
ADDED
@@ -0,0 +1,2614 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"ParamSize": 226,
|
4 |
+
"ParamBytes": 2384199680.0,
|
5 |
+
"BitsPerParam": 25.37623158078298
|
6 |
+
},
|
7 |
+
"records": [
|
8 |
+
{
|
9 |
+
"dataPath": "params_shard_0.bin",
|
10 |
+
"format": "raw-shard",
|
11 |
+
"nbytes": 311164928,
|
12 |
+
"records": [
|
13 |
+
{
|
14 |
+
"name": "model.embed_tokens.weight",
|
15 |
+
"shape": [
|
16 |
+
151936,
|
17 |
+
1024
|
18 |
+
],
|
19 |
+
"dtype": "float32",
|
20 |
+
"format": "f32-to-bf16",
|
21 |
+
"nbytes": 311164928,
|
22 |
+
"byteOffset": 0
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"md5sum": "4f615e4e204fe160829261879c8c4864"
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"dataPath": "params_shard_1.bin",
|
29 |
+
"format": "raw-shard",
|
30 |
+
"nbytes": 31463936,
|
31 |
+
"records": [
|
32 |
+
{
|
33 |
+
"name": "model.layers.0.input_layernorm.weight",
|
34 |
+
"shape": [
|
35 |
+
1024
|
36 |
+
],
|
37 |
+
"dtype": "float32",
|
38 |
+
"format": "f32-to-bf16",
|
39 |
+
"nbytes": 2048,
|
40 |
+
"byteOffset": 0
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"name": "model.layers.0.mlp.down_proj.weight",
|
44 |
+
"shape": [
|
45 |
+
1024,
|
46 |
+
3072
|
47 |
+
],
|
48 |
+
"dtype": "float32",
|
49 |
+
"format": "f32-to-bf16",
|
50 |
+
"nbytes": 6291456,
|
51 |
+
"byteOffset": 2048
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"name": "model.layers.0.mlp.gate_up_proj.weight",
|
55 |
+
"shape": [
|
56 |
+
6144,
|
57 |
+
1024
|
58 |
+
],
|
59 |
+
"dtype": "float32",
|
60 |
+
"format": "f32-to-bf16",
|
61 |
+
"nbytes": 12582912,
|
62 |
+
"byteOffset": 6293504
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
66 |
+
"shape": [
|
67 |
+
1024
|
68 |
+
],
|
69 |
+
"dtype": "float32",
|
70 |
+
"format": "f32-to-bf16",
|
71 |
+
"nbytes": 2048,
|
72 |
+
"byteOffset": 18876416
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"name": "model.layers.0.self_attn.k_norm.weight",
|
76 |
+
"shape": [
|
77 |
+
128
|
78 |
+
],
|
79 |
+
"dtype": "float32",
|
80 |
+
"format": "f32-to-bf16",
|
81 |
+
"nbytes": 256,
|
82 |
+
"byteOffset": 18878464
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"name": "model.layers.0.self_attn.c_attn.weight",
|
86 |
+
"shape": [
|
87 |
+
4096,
|
88 |
+
1024
|
89 |
+
],
|
90 |
+
"dtype": "float32",
|
91 |
+
"format": "f32-to-bf16",
|
92 |
+
"nbytes": 8388608,
|
93 |
+
"byteOffset": 18878720
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"name": "model.layers.0.self_attn.o_proj.weight",
|
97 |
+
"shape": [
|
98 |
+
1024,
|
99 |
+
2048
|
100 |
+
],
|
101 |
+
"dtype": "float32",
|
102 |
+
"format": "f32-to-bf16",
|
103 |
+
"nbytes": 4194304,
|
104 |
+
"byteOffset": 27267328
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"name": "model.layers.0.self_attn.q_norm.weight",
|
108 |
+
"shape": [
|
109 |
+
128
|
110 |
+
],
|
111 |
+
"dtype": "float32",
|
112 |
+
"format": "f32-to-bf16",
|
113 |
+
"nbytes": 256,
|
114 |
+
"byteOffset": 31461632
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"name": "model.layers.1.input_layernorm.weight",
|
118 |
+
"shape": [
|
119 |
+
1024
|
120 |
+
],
|
121 |
+
"dtype": "float32",
|
122 |
+
"format": "f32-to-bf16",
|
123 |
+
"nbytes": 2048,
|
124 |
+
"byteOffset": 31461888
|
125 |
+
}
|
126 |
+
],
|
127 |
+
"md5sum": "9e8c92fad1c6d7956d2f76d18b34c0c0"
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"dataPath": "params_shard_2.bin",
|
131 |
+
"format": "raw-shard",
|
132 |
+
"nbytes": 31461888,
|
133 |
+
"records": [
|
134 |
+
{
|
135 |
+
"name": "model.layers.1.mlp.down_proj.weight",
|
136 |
+
"shape": [
|
137 |
+
1024,
|
138 |
+
3072
|
139 |
+
],
|
140 |
+
"dtype": "float32",
|
141 |
+
"format": "f32-to-bf16",
|
142 |
+
"nbytes": 6291456,
|
143 |
+
"byteOffset": 0
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"name": "model.layers.1.mlp.gate_up_proj.weight",
|
147 |
+
"shape": [
|
148 |
+
6144,
|
149 |
+
1024
|
150 |
+
],
|
151 |
+
"dtype": "float32",
|
152 |
+
"format": "f32-to-bf16",
|
153 |
+
"nbytes": 12582912,
|
154 |
+
"byteOffset": 6291456
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
158 |
+
"shape": [
|
159 |
+
1024
|
160 |
+
],
|
161 |
+
"dtype": "float32",
|
162 |
+
"format": "f32-to-bf16",
|
163 |
+
"nbytes": 2048,
|
164 |
+
"byteOffset": 18874368
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"name": "model.layers.1.self_attn.k_norm.weight",
|
168 |
+
"shape": [
|
169 |
+
128
|
170 |
+
],
|
171 |
+
"dtype": "float32",
|
172 |
+
"format": "f32-to-bf16",
|
173 |
+
"nbytes": 256,
|
174 |
+
"byteOffset": 18876416
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"name": "model.layers.1.self_attn.c_attn.weight",
|
178 |
+
"shape": [
|
179 |
+
4096,
|
180 |
+
1024
|
181 |
+
],
|
182 |
+
"dtype": "float32",
|
183 |
+
"format": "f32-to-bf16",
|
184 |
+
"nbytes": 8388608,
|
185 |
+
"byteOffset": 18876672
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"name": "model.layers.1.self_attn.o_proj.weight",
|
189 |
+
"shape": [
|
190 |
+
1024,
|
191 |
+
2048
|
192 |
+
],
|
193 |
+
"dtype": "float32",
|
194 |
+
"format": "f32-to-bf16",
|
195 |
+
"nbytes": 4194304,
|
196 |
+
"byteOffset": 27265280
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"name": "model.layers.1.self_attn.q_norm.weight",
|
200 |
+
"shape": [
|
201 |
+
128
|
202 |
+
],
|
203 |
+
"dtype": "float32",
|
204 |
+
"format": "f32-to-bf16",
|
205 |
+
"nbytes": 256,
|
206 |
+
"byteOffset": 31459584
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"name": "model.layers.10.input_layernorm.weight",
|
210 |
+
"shape": [
|
211 |
+
1024
|
212 |
+
],
|
213 |
+
"dtype": "float32",
|
214 |
+
"format": "f32-to-bf16",
|
215 |
+
"nbytes": 2048,
|
216 |
+
"byteOffset": 31459840
|
217 |
+
}
|
218 |
+
],
|
219 |
+
"md5sum": "c74facda8699fab5c1fb909a0038eac3"
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"dataPath": "params_shard_3.bin",
|
223 |
+
"format": "raw-shard",
|
224 |
+
"nbytes": 31461888,
|
225 |
+
"records": [
|
226 |
+
{
|
227 |
+
"name": "model.layers.10.mlp.down_proj.weight",
|
228 |
+
"shape": [
|
229 |
+
1024,
|
230 |
+
3072
|
231 |
+
],
|
232 |
+
"dtype": "float32",
|
233 |
+
"format": "f32-to-bf16",
|
234 |
+
"nbytes": 6291456,
|
235 |
+
"byteOffset": 0
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"name": "model.layers.10.mlp.gate_up_proj.weight",
|
239 |
+
"shape": [
|
240 |
+
6144,
|
241 |
+
1024
|
242 |
+
],
|
243 |
+
"dtype": "float32",
|
244 |
+
"format": "f32-to-bf16",
|
245 |
+
"nbytes": 12582912,
|
246 |
+
"byteOffset": 6291456
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
250 |
+
"shape": [
|
251 |
+
1024
|
252 |
+
],
|
253 |
+
"dtype": "float32",
|
254 |
+
"format": "f32-to-bf16",
|
255 |
+
"nbytes": 2048,
|
256 |
+
"byteOffset": 18874368
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"name": "model.layers.10.self_attn.k_norm.weight",
|
260 |
+
"shape": [
|
261 |
+
128
|
262 |
+
],
|
263 |
+
"dtype": "float32",
|
264 |
+
"format": "f32-to-bf16",
|
265 |
+
"nbytes": 256,
|
266 |
+
"byteOffset": 18876416
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"name": "model.layers.10.self_attn.c_attn.weight",
|
270 |
+
"shape": [
|
271 |
+
4096,
|
272 |
+
1024
|
273 |
+
],
|
274 |
+
"dtype": "float32",
|
275 |
+
"format": "f32-to-bf16",
|
276 |
+
"nbytes": 8388608,
|
277 |
+
"byteOffset": 18876672
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"name": "model.layers.10.self_attn.o_proj.weight",
|
281 |
+
"shape": [
|
282 |
+
1024,
|
283 |
+
2048
|
284 |
+
],
|
285 |
+
"dtype": "float32",
|
286 |
+
"format": "f32-to-bf16",
|
287 |
+
"nbytes": 4194304,
|
288 |
+
"byteOffset": 27265280
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"name": "model.layers.10.self_attn.q_norm.weight",
|
292 |
+
"shape": [
|
293 |
+
128
|
294 |
+
],
|
295 |
+
"dtype": "float32",
|
296 |
+
"format": "f32-to-bf16",
|
297 |
+
"nbytes": 256,
|
298 |
+
"byteOffset": 31459584
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"name": "model.layers.11.input_layernorm.weight",
|
302 |
+
"shape": [
|
303 |
+
1024
|
304 |
+
],
|
305 |
+
"dtype": "float32",
|
306 |
+
"format": "f32-to-bf16",
|
307 |
+
"nbytes": 2048,
|
308 |
+
"byteOffset": 31459840
|
309 |
+
}
|
310 |
+
],
|
311 |
+
"md5sum": "79511a618a11a839e255c0d6b8117701"
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"dataPath": "params_shard_4.bin",
|
315 |
+
"format": "raw-shard",
|
316 |
+
"nbytes": 31461888,
|
317 |
+
"records": [
|
318 |
+
{
|
319 |
+
"name": "model.layers.11.mlp.down_proj.weight",
|
320 |
+
"shape": [
|
321 |
+
1024,
|
322 |
+
3072
|
323 |
+
],
|
324 |
+
"dtype": "float32",
|
325 |
+
"format": "f32-to-bf16",
|
326 |
+
"nbytes": 6291456,
|
327 |
+
"byteOffset": 0
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"name": "model.layers.11.mlp.gate_up_proj.weight",
|
331 |
+
"shape": [
|
332 |
+
6144,
|
333 |
+
1024
|
334 |
+
],
|
335 |
+
"dtype": "float32",
|
336 |
+
"format": "f32-to-bf16",
|
337 |
+
"nbytes": 12582912,
|
338 |
+
"byteOffset": 6291456
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
342 |
+
"shape": [
|
343 |
+
1024
|
344 |
+
],
|
345 |
+
"dtype": "float32",
|
346 |
+
"format": "f32-to-bf16",
|
347 |
+
"nbytes": 2048,
|
348 |
+
"byteOffset": 18874368
|
349 |
+
},
|
350 |
+
{
|
351 |
+
"name": "model.layers.11.self_attn.k_norm.weight",
|
352 |
+
"shape": [
|
353 |
+
128
|
354 |
+
],
|
355 |
+
"dtype": "float32",
|
356 |
+
"format": "f32-to-bf16",
|
357 |
+
"nbytes": 256,
|
358 |
+
"byteOffset": 18876416
|
359 |
+
},
|
360 |
+
{
|
361 |
+
"name": "model.layers.11.self_attn.c_attn.weight",
|
362 |
+
"shape": [
|
363 |
+
4096,
|
364 |
+
1024
|
365 |
+
],
|
366 |
+
"dtype": "float32",
|
367 |
+
"format": "f32-to-bf16",
|
368 |
+
"nbytes": 8388608,
|
369 |
+
"byteOffset": 18876672
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"name": "model.layers.11.self_attn.o_proj.weight",
|
373 |
+
"shape": [
|
374 |
+
1024,
|
375 |
+
2048
|
376 |
+
],
|
377 |
+
"dtype": "float32",
|
378 |
+
"format": "f32-to-bf16",
|
379 |
+
"nbytes": 4194304,
|
380 |
+
"byteOffset": 27265280
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"name": "model.layers.11.self_attn.q_norm.weight",
|
384 |
+
"shape": [
|
385 |
+
128
|
386 |
+
],
|
387 |
+
"dtype": "float32",
|
388 |
+
"format": "f32-to-bf16",
|
389 |
+
"nbytes": 256,
|
390 |
+
"byteOffset": 31459584
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"name": "model.layers.12.input_layernorm.weight",
|
394 |
+
"shape": [
|
395 |
+
1024
|
396 |
+
],
|
397 |
+
"dtype": "float32",
|
398 |
+
"format": "f32-to-bf16",
|
399 |
+
"nbytes": 2048,
|
400 |
+
"byteOffset": 31459840
|
401 |
+
}
|
402 |
+
],
|
403 |
+
"md5sum": "340f19886367858e06bb5b5367d20305"
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"dataPath": "params_shard_5.bin",
|
407 |
+
"format": "raw-shard",
|
408 |
+
"nbytes": 31461888,
|
409 |
+
"records": [
|
410 |
+
{
|
411 |
+
"name": "model.layers.12.mlp.down_proj.weight",
|
412 |
+
"shape": [
|
413 |
+
1024,
|
414 |
+
3072
|
415 |
+
],
|
416 |
+
"dtype": "float32",
|
417 |
+
"format": "f32-to-bf16",
|
418 |
+
"nbytes": 6291456,
|
419 |
+
"byteOffset": 0
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"name": "model.layers.12.mlp.gate_up_proj.weight",
|
423 |
+
"shape": [
|
424 |
+
6144,
|
425 |
+
1024
|
426 |
+
],
|
427 |
+
"dtype": "float32",
|
428 |
+
"format": "f32-to-bf16",
|
429 |
+
"nbytes": 12582912,
|
430 |
+
"byteOffset": 6291456
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
434 |
+
"shape": [
|
435 |
+
1024
|
436 |
+
],
|
437 |
+
"dtype": "float32",
|
438 |
+
"format": "f32-to-bf16",
|
439 |
+
"nbytes": 2048,
|
440 |
+
"byteOffset": 18874368
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"name": "model.layers.12.self_attn.k_norm.weight",
|
444 |
+
"shape": [
|
445 |
+
128
|
446 |
+
],
|
447 |
+
"dtype": "float32",
|
448 |
+
"format": "f32-to-bf16",
|
449 |
+
"nbytes": 256,
|
450 |
+
"byteOffset": 18876416
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"name": "model.layers.12.self_attn.c_attn.weight",
|
454 |
+
"shape": [
|
455 |
+
4096,
|
456 |
+
1024
|
457 |
+
],
|
458 |
+
"dtype": "float32",
|
459 |
+
"format": "f32-to-bf16",
|
460 |
+
"nbytes": 8388608,
|
461 |
+
"byteOffset": 18876672
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"name": "model.layers.12.self_attn.o_proj.weight",
|
465 |
+
"shape": [
|
466 |
+
1024,
|
467 |
+
2048
|
468 |
+
],
|
469 |
+
"dtype": "float32",
|
470 |
+
"format": "f32-to-bf16",
|
471 |
+
"nbytes": 4194304,
|
472 |
+
"byteOffset": 27265280
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"name": "model.layers.12.self_attn.q_norm.weight",
|
476 |
+
"shape": [
|
477 |
+
128
|
478 |
+
],
|
479 |
+
"dtype": "float32",
|
480 |
+
"format": "f32-to-bf16",
|
481 |
+
"nbytes": 256,
|
482 |
+
"byteOffset": 31459584
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"name": "model.layers.13.input_layernorm.weight",
|
486 |
+
"shape": [
|
487 |
+
1024
|
488 |
+
],
|
489 |
+
"dtype": "float32",
|
490 |
+
"format": "f32-to-bf16",
|
491 |
+
"nbytes": 2048,
|
492 |
+
"byteOffset": 31459840
|
493 |
+
}
|
494 |
+
],
|
495 |
+
"md5sum": "051d820dffb4d079fe6324e4fed50c4f"
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"dataPath": "params_shard_6.bin",
|
499 |
+
"format": "raw-shard",
|
500 |
+
"nbytes": 31461888,
|
501 |
+
"records": [
|
502 |
+
{
|
503 |
+
"name": "model.layers.13.mlp.down_proj.weight",
|
504 |
+
"shape": [
|
505 |
+
1024,
|
506 |
+
3072
|
507 |
+
],
|
508 |
+
"dtype": "float32",
|
509 |
+
"format": "f32-to-bf16",
|
510 |
+
"nbytes": 6291456,
|
511 |
+
"byteOffset": 0
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"name": "model.layers.13.mlp.gate_up_proj.weight",
|
515 |
+
"shape": [
|
516 |
+
6144,
|
517 |
+
1024
|
518 |
+
],
|
519 |
+
"dtype": "float32",
|
520 |
+
"format": "f32-to-bf16",
|
521 |
+
"nbytes": 12582912,
|
522 |
+
"byteOffset": 6291456
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
526 |
+
"shape": [
|
527 |
+
1024
|
528 |
+
],
|
529 |
+
"dtype": "float32",
|
530 |
+
"format": "f32-to-bf16",
|
531 |
+
"nbytes": 2048,
|
532 |
+
"byteOffset": 18874368
|
533 |
+
},
|
534 |
+
{
|
535 |
+
"name": "model.layers.13.self_attn.k_norm.weight",
|
536 |
+
"shape": [
|
537 |
+
128
|
538 |
+
],
|
539 |
+
"dtype": "float32",
|
540 |
+
"format": "f32-to-bf16",
|
541 |
+
"nbytes": 256,
|
542 |
+
"byteOffset": 18876416
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"name": "model.layers.13.self_attn.c_attn.weight",
|
546 |
+
"shape": [
|
547 |
+
4096,
|
548 |
+
1024
|
549 |
+
],
|
550 |
+
"dtype": "float32",
|
551 |
+
"format": "f32-to-bf16",
|
552 |
+
"nbytes": 8388608,
|
553 |
+
"byteOffset": 18876672
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"name": "model.layers.13.self_attn.o_proj.weight",
|
557 |
+
"shape": [
|
558 |
+
1024,
|
559 |
+
2048
|
560 |
+
],
|
561 |
+
"dtype": "float32",
|
562 |
+
"format": "f32-to-bf16",
|
563 |
+
"nbytes": 4194304,
|
564 |
+
"byteOffset": 27265280
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"name": "model.layers.13.self_attn.q_norm.weight",
|
568 |
+
"shape": [
|
569 |
+
128
|
570 |
+
],
|
571 |
+
"dtype": "float32",
|
572 |
+
"format": "f32-to-bf16",
|
573 |
+
"nbytes": 256,
|
574 |
+
"byteOffset": 31459584
|
575 |
+
},
|
576 |
+
{
|
577 |
+
"name": "model.layers.14.input_layernorm.weight",
|
578 |
+
"shape": [
|
579 |
+
1024
|
580 |
+
],
|
581 |
+
"dtype": "float32",
|
582 |
+
"format": "f32-to-bf16",
|
583 |
+
"nbytes": 2048,
|
584 |
+
"byteOffset": 31459840
|
585 |
+
}
|
586 |
+
],
|
587 |
+
"md5sum": "4aa584075dc763c62cfe3d5e58f17506"
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"dataPath": "params_shard_7.bin",
|
591 |
+
"format": "raw-shard",
|
592 |
+
"nbytes": 31461888,
|
593 |
+
"records": [
|
594 |
+
{
|
595 |
+
"name": "model.layers.14.mlp.down_proj.weight",
|
596 |
+
"shape": [
|
597 |
+
1024,
|
598 |
+
3072
|
599 |
+
],
|
600 |
+
"dtype": "float32",
|
601 |
+
"format": "f32-to-bf16",
|
602 |
+
"nbytes": 6291456,
|
603 |
+
"byteOffset": 0
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"name": "model.layers.14.mlp.gate_up_proj.weight",
|
607 |
+
"shape": [
|
608 |
+
6144,
|
609 |
+
1024
|
610 |
+
],
|
611 |
+
"dtype": "float32",
|
612 |
+
"format": "f32-to-bf16",
|
613 |
+
"nbytes": 12582912,
|
614 |
+
"byteOffset": 6291456
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"name": "model.layers.14.post_attention_layernorm.weight",
|
618 |
+
"shape": [
|
619 |
+
1024
|
620 |
+
],
|
621 |
+
"dtype": "float32",
|
622 |
+
"format": "f32-to-bf16",
|
623 |
+
"nbytes": 2048,
|
624 |
+
"byteOffset": 18874368
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"name": "model.layers.14.self_attn.k_norm.weight",
|
628 |
+
"shape": [
|
629 |
+
128
|
630 |
+
],
|
631 |
+
"dtype": "float32",
|
632 |
+
"format": "f32-to-bf16",
|
633 |
+
"nbytes": 256,
|
634 |
+
"byteOffset": 18876416
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"name": "model.layers.14.self_attn.c_attn.weight",
|
638 |
+
"shape": [
|
639 |
+
4096,
|
640 |
+
1024
|
641 |
+
],
|
642 |
+
"dtype": "float32",
|
643 |
+
"format": "f32-to-bf16",
|
644 |
+
"nbytes": 8388608,
|
645 |
+
"byteOffset": 18876672
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"name": "model.layers.14.self_attn.o_proj.weight",
|
649 |
+
"shape": [
|
650 |
+
1024,
|
651 |
+
2048
|
652 |
+
],
|
653 |
+
"dtype": "float32",
|
654 |
+
"format": "f32-to-bf16",
|
655 |
+
"nbytes": 4194304,
|
656 |
+
"byteOffset": 27265280
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"name": "model.layers.14.self_attn.q_norm.weight",
|
660 |
+
"shape": [
|
661 |
+
128
|
662 |
+
],
|
663 |
+
"dtype": "float32",
|
664 |
+
"format": "f32-to-bf16",
|
665 |
+
"nbytes": 256,
|
666 |
+
"byteOffset": 31459584
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"name": "model.layers.15.input_layernorm.weight",
|
670 |
+
"shape": [
|
671 |
+
1024
|
672 |
+
],
|
673 |
+
"dtype": "float32",
|
674 |
+
"format": "f32-to-bf16",
|
675 |
+
"nbytes": 2048,
|
676 |
+
"byteOffset": 31459840
|
677 |
+
}
|
678 |
+
],
|
679 |
+
"md5sum": "f3846e544c925d1caab9675209fb9b72"
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"dataPath": "params_shard_8.bin",
|
683 |
+
"format": "raw-shard",
|
684 |
+
"nbytes": 31461888,
|
685 |
+
"records": [
|
686 |
+
{
|
687 |
+
"name": "model.layers.15.mlp.down_proj.weight",
|
688 |
+
"shape": [
|
689 |
+
1024,
|
690 |
+
3072
|
691 |
+
],
|
692 |
+
"dtype": "float32",
|
693 |
+
"format": "f32-to-bf16",
|
694 |
+
"nbytes": 6291456,
|
695 |
+
"byteOffset": 0
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"name": "model.layers.15.mlp.gate_up_proj.weight",
|
699 |
+
"shape": [
|
700 |
+
6144,
|
701 |
+
1024
|
702 |
+
],
|
703 |
+
"dtype": "float32",
|
704 |
+
"format": "f32-to-bf16",
|
705 |
+
"nbytes": 12582912,
|
706 |
+
"byteOffset": 6291456
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"name": "model.layers.15.post_attention_layernorm.weight",
|
710 |
+
"shape": [
|
711 |
+
1024
|
712 |
+
],
|
713 |
+
"dtype": "float32",
|
714 |
+
"format": "f32-to-bf16",
|
715 |
+
"nbytes": 2048,
|
716 |
+
"byteOffset": 18874368
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"name": "model.layers.15.self_attn.k_norm.weight",
|
720 |
+
"shape": [
|
721 |
+
128
|
722 |
+
],
|
723 |
+
"dtype": "float32",
|
724 |
+
"format": "f32-to-bf16",
|
725 |
+
"nbytes": 256,
|
726 |
+
"byteOffset": 18876416
|
727 |
+
},
|
728 |
+
{
|
729 |
+
"name": "model.layers.15.self_attn.c_attn.weight",
|
730 |
+
"shape": [
|
731 |
+
4096,
|
732 |
+
1024
|
733 |
+
],
|
734 |
+
"dtype": "float32",
|
735 |
+
"format": "f32-to-bf16",
|
736 |
+
"nbytes": 8388608,
|
737 |
+
"byteOffset": 18876672
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"name": "model.layers.15.self_attn.o_proj.weight",
|
741 |
+
"shape": [
|
742 |
+
1024,
|
743 |
+
2048
|
744 |
+
],
|
745 |
+
"dtype": "float32",
|
746 |
+
"format": "f32-to-bf16",
|
747 |
+
"nbytes": 4194304,
|
748 |
+
"byteOffset": 27265280
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"name": "model.layers.15.self_attn.q_norm.weight",
|
752 |
+
"shape": [
|
753 |
+
128
|
754 |
+
],
|
755 |
+
"dtype": "float32",
|
756 |
+
"format": "f32-to-bf16",
|
757 |
+
"nbytes": 256,
|
758 |
+
"byteOffset": 31459584
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"name": "model.layers.16.input_layernorm.weight",
|
762 |
+
"shape": [
|
763 |
+
1024
|
764 |
+
],
|
765 |
+
"dtype": "float32",
|
766 |
+
"format": "f32-to-bf16",
|
767 |
+
"nbytes": 2048,
|
768 |
+
"byteOffset": 31459840
|
769 |
+
}
|
770 |
+
],
|
771 |
+
"md5sum": "4782b81576a4555a1f25d98dbcc3397e"
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"dataPath": "params_shard_9.bin",
|
775 |
+
"format": "raw-shard",
|
776 |
+
"nbytes": 31461888,
|
777 |
+
"records": [
|
778 |
+
{
|
779 |
+
"name": "model.layers.16.mlp.down_proj.weight",
|
780 |
+
"shape": [
|
781 |
+
1024,
|
782 |
+
3072
|
783 |
+
],
|
784 |
+
"dtype": "float32",
|
785 |
+
"format": "f32-to-bf16",
|
786 |
+
"nbytes": 6291456,
|
787 |
+
"byteOffset": 0
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"name": "model.layers.16.mlp.gate_up_proj.weight",
|
791 |
+
"shape": [
|
792 |
+
6144,
|
793 |
+
1024
|
794 |
+
],
|
795 |
+
"dtype": "float32",
|
796 |
+
"format": "f32-to-bf16",
|
797 |
+
"nbytes": 12582912,
|
798 |
+
"byteOffset": 6291456
|
799 |
+
},
|
800 |
+
{
|
801 |
+
"name": "model.layers.16.post_attention_layernorm.weight",
|
802 |
+
"shape": [
|
803 |
+
1024
|
804 |
+
],
|
805 |
+
"dtype": "float32",
|
806 |
+
"format": "f32-to-bf16",
|
807 |
+
"nbytes": 2048,
|
808 |
+
"byteOffset": 18874368
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"name": "model.layers.16.self_attn.k_norm.weight",
|
812 |
+
"shape": [
|
813 |
+
128
|
814 |
+
],
|
815 |
+
"dtype": "float32",
|
816 |
+
"format": "f32-to-bf16",
|
817 |
+
"nbytes": 256,
|
818 |
+
"byteOffset": 18876416
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"name": "model.layers.16.self_attn.c_attn.weight",
|
822 |
+
"shape": [
|
823 |
+
4096,
|
824 |
+
1024
|
825 |
+
],
|
826 |
+
"dtype": "float32",
|
827 |
+
"format": "f32-to-bf16",
|
828 |
+
"nbytes": 8388608,
|
829 |
+
"byteOffset": 18876672
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"name": "model.layers.16.self_attn.o_proj.weight",
|
833 |
+
"shape": [
|
834 |
+
1024,
|
835 |
+
2048
|
836 |
+
],
|
837 |
+
"dtype": "float32",
|
838 |
+
"format": "f32-to-bf16",
|
839 |
+
"nbytes": 4194304,
|
840 |
+
"byteOffset": 27265280
|
841 |
+
},
|
842 |
+
{
|
843 |
+
"name": "model.layers.16.self_attn.q_norm.weight",
|
844 |
+
"shape": [
|
845 |
+
128
|
846 |
+
],
|
847 |
+
"dtype": "float32",
|
848 |
+
"format": "f32-to-bf16",
|
849 |
+
"nbytes": 256,
|
850 |
+
"byteOffset": 31459584
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"name": "model.layers.17.input_layernorm.weight",
|
854 |
+
"shape": [
|
855 |
+
1024
|
856 |
+
],
|
857 |
+
"dtype": "float32",
|
858 |
+
"format": "f32-to-bf16",
|
859 |
+
"nbytes": 2048,
|
860 |
+
"byteOffset": 31459840
|
861 |
+
}
|
862 |
+
],
|
863 |
+
"md5sum": "50a506dc9852c1c7be39db6bbbb71bc4"
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"dataPath": "params_shard_10.bin",
|
867 |
+
"format": "raw-shard",
|
868 |
+
"nbytes": 31461888,
|
869 |
+
"records": [
|
870 |
+
{
|
871 |
+
"name": "model.layers.17.mlp.down_proj.weight",
|
872 |
+
"shape": [
|
873 |
+
1024,
|
874 |
+
3072
|
875 |
+
],
|
876 |
+
"dtype": "float32",
|
877 |
+
"format": "f32-to-bf16",
|
878 |
+
"nbytes": 6291456,
|
879 |
+
"byteOffset": 0
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"name": "model.layers.17.mlp.gate_up_proj.weight",
|
883 |
+
"shape": [
|
884 |
+
6144,
|
885 |
+
1024
|
886 |
+
],
|
887 |
+
"dtype": "float32",
|
888 |
+
"format": "f32-to-bf16",
|
889 |
+
"nbytes": 12582912,
|
890 |
+
"byteOffset": 6291456
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"name": "model.layers.17.post_attention_layernorm.weight",
|
894 |
+
"shape": [
|
895 |
+
1024
|
896 |
+
],
|
897 |
+
"dtype": "float32",
|
898 |
+
"format": "f32-to-bf16",
|
899 |
+
"nbytes": 2048,
|
900 |
+
"byteOffset": 18874368
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"name": "model.layers.17.self_attn.k_norm.weight",
|
904 |
+
"shape": [
|
905 |
+
128
|
906 |
+
],
|
907 |
+
"dtype": "float32",
|
908 |
+
"format": "f32-to-bf16",
|
909 |
+
"nbytes": 256,
|
910 |
+
"byteOffset": 18876416
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"name": "model.layers.17.self_attn.c_attn.weight",
|
914 |
+
"shape": [
|
915 |
+
4096,
|
916 |
+
1024
|
917 |
+
],
|
918 |
+
"dtype": "float32",
|
919 |
+
"format": "f32-to-bf16",
|
920 |
+
"nbytes": 8388608,
|
921 |
+
"byteOffset": 18876672
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"name": "model.layers.17.self_attn.o_proj.weight",
|
925 |
+
"shape": [
|
926 |
+
1024,
|
927 |
+
2048
|
928 |
+
],
|
929 |
+
"dtype": "float32",
|
930 |
+
"format": "f32-to-bf16",
|
931 |
+
"nbytes": 4194304,
|
932 |
+
"byteOffset": 27265280
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"name": "model.layers.17.self_attn.q_norm.weight",
|
936 |
+
"shape": [
|
937 |
+
128
|
938 |
+
],
|
939 |
+
"dtype": "float32",
|
940 |
+
"format": "f32-to-bf16",
|
941 |
+
"nbytes": 256,
|
942 |
+
"byteOffset": 31459584
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"name": "model.layers.18.input_layernorm.weight",
|
946 |
+
"shape": [
|
947 |
+
1024
|
948 |
+
],
|
949 |
+
"dtype": "float32",
|
950 |
+
"format": "f32-to-bf16",
|
951 |
+
"nbytes": 2048,
|
952 |
+
"byteOffset": 31459840
|
953 |
+
}
|
954 |
+
],
|
955 |
+
"md5sum": "28226cd94e7b0b9cb620911de11ec28c"
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"dataPath": "params_shard_11.bin",
|
959 |
+
"format": "raw-shard",
|
960 |
+
"nbytes": 31461888,
|
961 |
+
"records": [
|
962 |
+
{
|
963 |
+
"name": "model.layers.18.mlp.down_proj.weight",
|
964 |
+
"shape": [
|
965 |
+
1024,
|
966 |
+
3072
|
967 |
+
],
|
968 |
+
"dtype": "float32",
|
969 |
+
"format": "f32-to-bf16",
|
970 |
+
"nbytes": 6291456,
|
971 |
+
"byteOffset": 0
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"name": "model.layers.18.mlp.gate_up_proj.weight",
|
975 |
+
"shape": [
|
976 |
+
6144,
|
977 |
+
1024
|
978 |
+
],
|
979 |
+
"dtype": "float32",
|
980 |
+
"format": "f32-to-bf16",
|
981 |
+
"nbytes": 12582912,
|
982 |
+
"byteOffset": 6291456
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"name": "model.layers.18.post_attention_layernorm.weight",
|
986 |
+
"shape": [
|
987 |
+
1024
|
988 |
+
],
|
989 |
+
"dtype": "float32",
|
990 |
+
"format": "f32-to-bf16",
|
991 |
+
"nbytes": 2048,
|
992 |
+
"byteOffset": 18874368
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"name": "model.layers.18.self_attn.k_norm.weight",
|
996 |
+
"shape": [
|
997 |
+
128
|
998 |
+
],
|
999 |
+
"dtype": "float32",
|
1000 |
+
"format": "f32-to-bf16",
|
1001 |
+
"nbytes": 256,
|
1002 |
+
"byteOffset": 18876416
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"name": "model.layers.18.self_attn.c_attn.weight",
|
1006 |
+
"shape": [
|
1007 |
+
4096,
|
1008 |
+
1024
|
1009 |
+
],
|
1010 |
+
"dtype": "float32",
|
1011 |
+
"format": "f32-to-bf16",
|
1012 |
+
"nbytes": 8388608,
|
1013 |
+
"byteOffset": 18876672
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"name": "model.layers.18.self_attn.o_proj.weight",
|
1017 |
+
"shape": [
|
1018 |
+
1024,
|
1019 |
+
2048
|
1020 |
+
],
|
1021 |
+
"dtype": "float32",
|
1022 |
+
"format": "f32-to-bf16",
|
1023 |
+
"nbytes": 4194304,
|
1024 |
+
"byteOffset": 27265280
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"name": "model.layers.18.self_attn.q_norm.weight",
|
1028 |
+
"shape": [
|
1029 |
+
128
|
1030 |
+
],
|
1031 |
+
"dtype": "float32",
|
1032 |
+
"format": "f32-to-bf16",
|
1033 |
+
"nbytes": 256,
|
1034 |
+
"byteOffset": 31459584
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"name": "model.layers.19.input_layernorm.weight",
|
1038 |
+
"shape": [
|
1039 |
+
1024
|
1040 |
+
],
|
1041 |
+
"dtype": "float32",
|
1042 |
+
"format": "f32-to-bf16",
|
1043 |
+
"nbytes": 2048,
|
1044 |
+
"byteOffset": 31459840
|
1045 |
+
}
|
1046 |
+
],
|
1047 |
+
"md5sum": "961f8e1a308774dc0fd86312259d7c82"
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"dataPath": "params_shard_12.bin",
|
1051 |
+
"format": "raw-shard",
|
1052 |
+
"nbytes": 31461888,
|
1053 |
+
"records": [
|
1054 |
+
{
|
1055 |
+
"name": "model.layers.19.mlp.down_proj.weight",
|
1056 |
+
"shape": [
|
1057 |
+
1024,
|
1058 |
+
3072
|
1059 |
+
],
|
1060 |
+
"dtype": "float32",
|
1061 |
+
"format": "f32-to-bf16",
|
1062 |
+
"nbytes": 6291456,
|
1063 |
+
"byteOffset": 0
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"name": "model.layers.19.mlp.gate_up_proj.weight",
|
1067 |
+
"shape": [
|
1068 |
+
6144,
|
1069 |
+
1024
|
1070 |
+
],
|
1071 |
+
"dtype": "float32",
|
1072 |
+
"format": "f32-to-bf16",
|
1073 |
+
"nbytes": 12582912,
|
1074 |
+
"byteOffset": 6291456
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"name": "model.layers.19.post_attention_layernorm.weight",
|
1078 |
+
"shape": [
|
1079 |
+
1024
|
1080 |
+
],
|
1081 |
+
"dtype": "float32",
|
1082 |
+
"format": "f32-to-bf16",
|
1083 |
+
"nbytes": 2048,
|
1084 |
+
"byteOffset": 18874368
|
1085 |
+
},
|
1086 |
+
{
|
1087 |
+
"name": "model.layers.19.self_attn.k_norm.weight",
|
1088 |
+
"shape": [
|
1089 |
+
128
|
1090 |
+
],
|
1091 |
+
"dtype": "float32",
|
1092 |
+
"format": "f32-to-bf16",
|
1093 |
+
"nbytes": 256,
|
1094 |
+
"byteOffset": 18876416
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"name": "model.layers.19.self_attn.c_attn.weight",
|
1098 |
+
"shape": [
|
1099 |
+
4096,
|
1100 |
+
1024
|
1101 |
+
],
|
1102 |
+
"dtype": "float32",
|
1103 |
+
"format": "f32-to-bf16",
|
1104 |
+
"nbytes": 8388608,
|
1105 |
+
"byteOffset": 18876672
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"name": "model.layers.19.self_attn.o_proj.weight",
|
1109 |
+
"shape": [
|
1110 |
+
1024,
|
1111 |
+
2048
|
1112 |
+
],
|
1113 |
+
"dtype": "float32",
|
1114 |
+
"format": "f32-to-bf16",
|
1115 |
+
"nbytes": 4194304,
|
1116 |
+
"byteOffset": 27265280
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"name": "model.layers.19.self_attn.q_norm.weight",
|
1120 |
+
"shape": [
|
1121 |
+
128
|
1122 |
+
],
|
1123 |
+
"dtype": "float32",
|
1124 |
+
"format": "f32-to-bf16",
|
1125 |
+
"nbytes": 256,
|
1126 |
+
"byteOffset": 31459584
|
1127 |
+
},
|
1128 |
+
{
|
1129 |
+
"name": "model.layers.2.input_layernorm.weight",
|
1130 |
+
"shape": [
|
1131 |
+
1024
|
1132 |
+
],
|
1133 |
+
"dtype": "float32",
|
1134 |
+
"format": "f32-to-bf16",
|
1135 |
+
"nbytes": 2048,
|
1136 |
+
"byteOffset": 31459840
|
1137 |
+
}
|
1138 |
+
],
|
1139 |
+
"md5sum": "f17374b039b0e7a53080d4e8c61f1f16"
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"dataPath": "params_shard_13.bin",
|
1143 |
+
"format": "raw-shard",
|
1144 |
+
"nbytes": 31461888,
|
1145 |
+
"records": [
|
1146 |
+
{
|
1147 |
+
"name": "model.layers.2.mlp.down_proj.weight",
|
1148 |
+
"shape": [
|
1149 |
+
1024,
|
1150 |
+
3072
|
1151 |
+
],
|
1152 |
+
"dtype": "float32",
|
1153 |
+
"format": "f32-to-bf16",
|
1154 |
+
"nbytes": 6291456,
|
1155 |
+
"byteOffset": 0
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"name": "model.layers.2.mlp.gate_up_proj.weight",
|
1159 |
+
"shape": [
|
1160 |
+
6144,
|
1161 |
+
1024
|
1162 |
+
],
|
1163 |
+
"dtype": "float32",
|
1164 |
+
"format": "f32-to-bf16",
|
1165 |
+
"nbytes": 12582912,
|
1166 |
+
"byteOffset": 6291456
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
1170 |
+
"shape": [
|
1171 |
+
1024
|
1172 |
+
],
|
1173 |
+
"dtype": "float32",
|
1174 |
+
"format": "f32-to-bf16",
|
1175 |
+
"nbytes": 2048,
|
1176 |
+
"byteOffset": 18874368
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"name": "model.layers.2.self_attn.k_norm.weight",
|
1180 |
+
"shape": [
|
1181 |
+
128
|
1182 |
+
],
|
1183 |
+
"dtype": "float32",
|
1184 |
+
"format": "f32-to-bf16",
|
1185 |
+
"nbytes": 256,
|
1186 |
+
"byteOffset": 18876416
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"name": "model.layers.2.self_attn.c_attn.weight",
|
1190 |
+
"shape": [
|
1191 |
+
4096,
|
1192 |
+
1024
|
1193 |
+
],
|
1194 |
+
"dtype": "float32",
|
1195 |
+
"format": "f32-to-bf16",
|
1196 |
+
"nbytes": 8388608,
|
1197 |
+
"byteOffset": 18876672
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"name": "model.layers.2.self_attn.o_proj.weight",
|
1201 |
+
"shape": [
|
1202 |
+
1024,
|
1203 |
+
2048
|
1204 |
+
],
|
1205 |
+
"dtype": "float32",
|
1206 |
+
"format": "f32-to-bf16",
|
1207 |
+
"nbytes": 4194304,
|
1208 |
+
"byteOffset": 27265280
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"name": "model.layers.2.self_attn.q_norm.weight",
|
1212 |
+
"shape": [
|
1213 |
+
128
|
1214 |
+
],
|
1215 |
+
"dtype": "float32",
|
1216 |
+
"format": "f32-to-bf16",
|
1217 |
+
"nbytes": 256,
|
1218 |
+
"byteOffset": 31459584
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"name": "model.layers.20.input_layernorm.weight",
|
1222 |
+
"shape": [
|
1223 |
+
1024
|
1224 |
+
],
|
1225 |
+
"dtype": "float32",
|
1226 |
+
"format": "f32-to-bf16",
|
1227 |
+
"nbytes": 2048,
|
1228 |
+
"byteOffset": 31459840
|
1229 |
+
}
|
1230 |
+
],
|
1231 |
+
"md5sum": "7951ac8ebc3690aa9df718dfb599eb7b"
|
1232 |
+
},
|
1233 |
+
{
|
1234 |
+
"dataPath": "params_shard_14.bin",
|
1235 |
+
"format": "raw-shard",
|
1236 |
+
"nbytes": 31461888,
|
1237 |
+
"records": [
|
1238 |
+
{
|
1239 |
+
"name": "model.layers.20.mlp.down_proj.weight",
|
1240 |
+
"shape": [
|
1241 |
+
1024,
|
1242 |
+
3072
|
1243 |
+
],
|
1244 |
+
"dtype": "float32",
|
1245 |
+
"format": "f32-to-bf16",
|
1246 |
+
"nbytes": 6291456,
|
1247 |
+
"byteOffset": 0
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"name": "model.layers.20.mlp.gate_up_proj.weight",
|
1251 |
+
"shape": [
|
1252 |
+
6144,
|
1253 |
+
1024
|
1254 |
+
],
|
1255 |
+
"dtype": "float32",
|
1256 |
+
"format": "f32-to-bf16",
|
1257 |
+
"nbytes": 12582912,
|
1258 |
+
"byteOffset": 6291456
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"name": "model.layers.20.post_attention_layernorm.weight",
|
1262 |
+
"shape": [
|
1263 |
+
1024
|
1264 |
+
],
|
1265 |
+
"dtype": "float32",
|
1266 |
+
"format": "f32-to-bf16",
|
1267 |
+
"nbytes": 2048,
|
1268 |
+
"byteOffset": 18874368
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"name": "model.layers.20.self_attn.k_norm.weight",
|
1272 |
+
"shape": [
|
1273 |
+
128
|
1274 |
+
],
|
1275 |
+
"dtype": "float32",
|
1276 |
+
"format": "f32-to-bf16",
|
1277 |
+
"nbytes": 256,
|
1278 |
+
"byteOffset": 18876416
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"name": "model.layers.20.self_attn.c_attn.weight",
|
1282 |
+
"shape": [
|
1283 |
+
4096,
|
1284 |
+
1024
|
1285 |
+
],
|
1286 |
+
"dtype": "float32",
|
1287 |
+
"format": "f32-to-bf16",
|
1288 |
+
"nbytes": 8388608,
|
1289 |
+
"byteOffset": 18876672
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"name": "model.layers.20.self_attn.o_proj.weight",
|
1293 |
+
"shape": [
|
1294 |
+
1024,
|
1295 |
+
2048
|
1296 |
+
],
|
1297 |
+
"dtype": "float32",
|
1298 |
+
"format": "f32-to-bf16",
|
1299 |
+
"nbytes": 4194304,
|
1300 |
+
"byteOffset": 27265280
|
1301 |
+
},
|
1302 |
+
{
|
1303 |
+
"name": "model.layers.20.self_attn.q_norm.weight",
|
1304 |
+
"shape": [
|
1305 |
+
128
|
1306 |
+
],
|
1307 |
+
"dtype": "float32",
|
1308 |
+
"format": "f32-to-bf16",
|
1309 |
+
"nbytes": 256,
|
1310 |
+
"byteOffset": 31459584
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"name": "model.layers.21.input_layernorm.weight",
|
1314 |
+
"shape": [
|
1315 |
+
1024
|
1316 |
+
],
|
1317 |
+
"dtype": "float32",
|
1318 |
+
"format": "f32-to-bf16",
|
1319 |
+
"nbytes": 2048,
|
1320 |
+
"byteOffset": 31459840
|
1321 |
+
}
|
1322 |
+
],
|
1323 |
+
"md5sum": "a17e66b0197f5f796edc26b7c0b60a79"
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"dataPath": "params_shard_15.bin",
|
1327 |
+
"format": "raw-shard",
|
1328 |
+
"nbytes": 31461888,
|
1329 |
+
"records": [
|
1330 |
+
{
|
1331 |
+
"name": "model.layers.21.mlp.down_proj.weight",
|
1332 |
+
"shape": [
|
1333 |
+
1024,
|
1334 |
+
3072
|
1335 |
+
],
|
1336 |
+
"dtype": "float32",
|
1337 |
+
"format": "f32-to-bf16",
|
1338 |
+
"nbytes": 6291456,
|
1339 |
+
"byteOffset": 0
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"name": "model.layers.21.mlp.gate_up_proj.weight",
|
1343 |
+
"shape": [
|
1344 |
+
6144,
|
1345 |
+
1024
|
1346 |
+
],
|
1347 |
+
"dtype": "float32",
|
1348 |
+
"format": "f32-to-bf16",
|
1349 |
+
"nbytes": 12582912,
|
1350 |
+
"byteOffset": 6291456
|
1351 |
+
},
|
1352 |
+
{
|
1353 |
+
"name": "model.layers.21.post_attention_layernorm.weight",
|
1354 |
+
"shape": [
|
1355 |
+
1024
|
1356 |
+
],
|
1357 |
+
"dtype": "float32",
|
1358 |
+
"format": "f32-to-bf16",
|
1359 |
+
"nbytes": 2048,
|
1360 |
+
"byteOffset": 18874368
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"name": "model.layers.21.self_attn.k_norm.weight",
|
1364 |
+
"shape": [
|
1365 |
+
128
|
1366 |
+
],
|
1367 |
+
"dtype": "float32",
|
1368 |
+
"format": "f32-to-bf16",
|
1369 |
+
"nbytes": 256,
|
1370 |
+
"byteOffset": 18876416
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"name": "model.layers.21.self_attn.c_attn.weight",
|
1374 |
+
"shape": [
|
1375 |
+
4096,
|
1376 |
+
1024
|
1377 |
+
],
|
1378 |
+
"dtype": "float32",
|
1379 |
+
"format": "f32-to-bf16",
|
1380 |
+
"nbytes": 8388608,
|
1381 |
+
"byteOffset": 18876672
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"name": "model.layers.21.self_attn.o_proj.weight",
|
1385 |
+
"shape": [
|
1386 |
+
1024,
|
1387 |
+
2048
|
1388 |
+
],
|
1389 |
+
"dtype": "float32",
|
1390 |
+
"format": "f32-to-bf16",
|
1391 |
+
"nbytes": 4194304,
|
1392 |
+
"byteOffset": 27265280
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"name": "model.layers.21.self_attn.q_norm.weight",
|
1396 |
+
"shape": [
|
1397 |
+
128
|
1398 |
+
],
|
1399 |
+
"dtype": "float32",
|
1400 |
+
"format": "f32-to-bf16",
|
1401 |
+
"nbytes": 256,
|
1402 |
+
"byteOffset": 31459584
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"name": "model.layers.22.input_layernorm.weight",
|
1406 |
+
"shape": [
|
1407 |
+
1024
|
1408 |
+
],
|
1409 |
+
"dtype": "float32",
|
1410 |
+
"format": "f32-to-bf16",
|
1411 |
+
"nbytes": 2048,
|
1412 |
+
"byteOffset": 31459840
|
1413 |
+
}
|
1414 |
+
],
|
1415 |
+
"md5sum": "29dc75f0a0de71a20a19dc04d6ec2fe8"
|
1416 |
+
},
|
1417 |
+
{
|
1418 |
+
"dataPath": "params_shard_16.bin",
|
1419 |
+
"format": "raw-shard",
|
1420 |
+
"nbytes": 31461888,
|
1421 |
+
"records": [
|
1422 |
+
{
|
1423 |
+
"name": "model.layers.22.mlp.down_proj.weight",
|
1424 |
+
"shape": [
|
1425 |
+
1024,
|
1426 |
+
3072
|
1427 |
+
],
|
1428 |
+
"dtype": "float32",
|
1429 |
+
"format": "f32-to-bf16",
|
1430 |
+
"nbytes": 6291456,
|
1431 |
+
"byteOffset": 0
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"name": "model.layers.22.mlp.gate_up_proj.weight",
|
1435 |
+
"shape": [
|
1436 |
+
6144,
|
1437 |
+
1024
|
1438 |
+
],
|
1439 |
+
"dtype": "float32",
|
1440 |
+
"format": "f32-to-bf16",
|
1441 |
+
"nbytes": 12582912,
|
1442 |
+
"byteOffset": 6291456
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"name": "model.layers.22.post_attention_layernorm.weight",
|
1446 |
+
"shape": [
|
1447 |
+
1024
|
1448 |
+
],
|
1449 |
+
"dtype": "float32",
|
1450 |
+
"format": "f32-to-bf16",
|
1451 |
+
"nbytes": 2048,
|
1452 |
+
"byteOffset": 18874368
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"name": "model.layers.22.self_attn.k_norm.weight",
|
1456 |
+
"shape": [
|
1457 |
+
128
|
1458 |
+
],
|
1459 |
+
"dtype": "float32",
|
1460 |
+
"format": "f32-to-bf16",
|
1461 |
+
"nbytes": 256,
|
1462 |
+
"byteOffset": 18876416
|
1463 |
+
},
|
1464 |
+
{
|
1465 |
+
"name": "model.layers.22.self_attn.c_attn.weight",
|
1466 |
+
"shape": [
|
1467 |
+
4096,
|
1468 |
+
1024
|
1469 |
+
],
|
1470 |
+
"dtype": "float32",
|
1471 |
+
"format": "f32-to-bf16",
|
1472 |
+
"nbytes": 8388608,
|
1473 |
+
"byteOffset": 18876672
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"name": "model.layers.22.self_attn.o_proj.weight",
|
1477 |
+
"shape": [
|
1478 |
+
1024,
|
1479 |
+
2048
|
1480 |
+
],
|
1481 |
+
"dtype": "float32",
|
1482 |
+
"format": "f32-to-bf16",
|
1483 |
+
"nbytes": 4194304,
|
1484 |
+
"byteOffset": 27265280
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"name": "model.layers.22.self_attn.q_norm.weight",
|
1488 |
+
"shape": [
|
1489 |
+
128
|
1490 |
+
],
|
1491 |
+
"dtype": "float32",
|
1492 |
+
"format": "f32-to-bf16",
|
1493 |
+
"nbytes": 256,
|
1494 |
+
"byteOffset": 31459584
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"name": "model.layers.23.input_layernorm.weight",
|
1498 |
+
"shape": [
|
1499 |
+
1024
|
1500 |
+
],
|
1501 |
+
"dtype": "float32",
|
1502 |
+
"format": "f32-to-bf16",
|
1503 |
+
"nbytes": 2048,
|
1504 |
+
"byteOffset": 31459840
|
1505 |
+
}
|
1506 |
+
],
|
1507 |
+
"md5sum": "77370b671251a8b0f10de8721da680eb"
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"dataPath": "params_shard_17.bin",
|
1511 |
+
"format": "raw-shard",
|
1512 |
+
"nbytes": 31461888,
|
1513 |
+
"records": [
|
1514 |
+
{
|
1515 |
+
"name": "model.layers.23.mlp.down_proj.weight",
|
1516 |
+
"shape": [
|
1517 |
+
1024,
|
1518 |
+
3072
|
1519 |
+
],
|
1520 |
+
"dtype": "float32",
|
1521 |
+
"format": "f32-to-bf16",
|
1522 |
+
"nbytes": 6291456,
|
1523 |
+
"byteOffset": 0
|
1524 |
+
},
|
1525 |
+
{
|
1526 |
+
"name": "model.layers.23.mlp.gate_up_proj.weight",
|
1527 |
+
"shape": [
|
1528 |
+
6144,
|
1529 |
+
1024
|
1530 |
+
],
|
1531 |
+
"dtype": "float32",
|
1532 |
+
"format": "f32-to-bf16",
|
1533 |
+
"nbytes": 12582912,
|
1534 |
+
"byteOffset": 6291456
|
1535 |
+
},
|
1536 |
+
{
|
1537 |
+
"name": "model.layers.23.post_attention_layernorm.weight",
|
1538 |
+
"shape": [
|
1539 |
+
1024
|
1540 |
+
],
|
1541 |
+
"dtype": "float32",
|
1542 |
+
"format": "f32-to-bf16",
|
1543 |
+
"nbytes": 2048,
|
1544 |
+
"byteOffset": 18874368
|
1545 |
+
},
|
1546 |
+
{
|
1547 |
+
"name": "model.layers.23.self_attn.k_norm.weight",
|
1548 |
+
"shape": [
|
1549 |
+
128
|
1550 |
+
],
|
1551 |
+
"dtype": "float32",
|
1552 |
+
"format": "f32-to-bf16",
|
1553 |
+
"nbytes": 256,
|
1554 |
+
"byteOffset": 18876416
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"name": "model.layers.23.self_attn.c_attn.weight",
|
1558 |
+
"shape": [
|
1559 |
+
4096,
|
1560 |
+
1024
|
1561 |
+
],
|
1562 |
+
"dtype": "float32",
|
1563 |
+
"format": "f32-to-bf16",
|
1564 |
+
"nbytes": 8388608,
|
1565 |
+
"byteOffset": 18876672
|
1566 |
+
},
|
1567 |
+
{
|
1568 |
+
"name": "model.layers.23.self_attn.o_proj.weight",
|
1569 |
+
"shape": [
|
1570 |
+
1024,
|
1571 |
+
2048
|
1572 |
+
],
|
1573 |
+
"dtype": "float32",
|
1574 |
+
"format": "f32-to-bf16",
|
1575 |
+
"nbytes": 4194304,
|
1576 |
+
"byteOffset": 27265280
|
1577 |
+
},
|
1578 |
+
{
|
1579 |
+
"name": "model.layers.23.self_attn.q_norm.weight",
|
1580 |
+
"shape": [
|
1581 |
+
128
|
1582 |
+
],
|
1583 |
+
"dtype": "float32",
|
1584 |
+
"format": "f32-to-bf16",
|
1585 |
+
"nbytes": 256,
|
1586 |
+
"byteOffset": 31459584
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"name": "model.layers.24.input_layernorm.weight",
|
1590 |
+
"shape": [
|
1591 |
+
1024
|
1592 |
+
],
|
1593 |
+
"dtype": "float32",
|
1594 |
+
"format": "f32-to-bf16",
|
1595 |
+
"nbytes": 2048,
|
1596 |
+
"byteOffset": 31459840
|
1597 |
+
}
|
1598 |
+
],
|
1599 |
+
"md5sum": "e1b3dd47fb933da1144e2d4ee03a6447"
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"dataPath": "params_shard_18.bin",
|
1603 |
+
"format": "raw-shard",
|
1604 |
+
"nbytes": 31461888,
|
1605 |
+
"records": [
|
1606 |
+
{
|
1607 |
+
"name": "model.layers.24.mlp.down_proj.weight",
|
1608 |
+
"shape": [
|
1609 |
+
1024,
|
1610 |
+
3072
|
1611 |
+
],
|
1612 |
+
"dtype": "float32",
|
1613 |
+
"format": "f32-to-bf16",
|
1614 |
+
"nbytes": 6291456,
|
1615 |
+
"byteOffset": 0
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"name": "model.layers.24.mlp.gate_up_proj.weight",
|
1619 |
+
"shape": [
|
1620 |
+
6144,
|
1621 |
+
1024
|
1622 |
+
],
|
1623 |
+
"dtype": "float32",
|
1624 |
+
"format": "f32-to-bf16",
|
1625 |
+
"nbytes": 12582912,
|
1626 |
+
"byteOffset": 6291456
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"name": "model.layers.24.post_attention_layernorm.weight",
|
1630 |
+
"shape": [
|
1631 |
+
1024
|
1632 |
+
],
|
1633 |
+
"dtype": "float32",
|
1634 |
+
"format": "f32-to-bf16",
|
1635 |
+
"nbytes": 2048,
|
1636 |
+
"byteOffset": 18874368
|
1637 |
+
},
|
1638 |
+
{
|
1639 |
+
"name": "model.layers.24.self_attn.k_norm.weight",
|
1640 |
+
"shape": [
|
1641 |
+
128
|
1642 |
+
],
|
1643 |
+
"dtype": "float32",
|
1644 |
+
"format": "f32-to-bf16",
|
1645 |
+
"nbytes": 256,
|
1646 |
+
"byteOffset": 18876416
|
1647 |
+
},
|
1648 |
+
{
|
1649 |
+
"name": "model.layers.24.self_attn.c_attn.weight",
|
1650 |
+
"shape": [
|
1651 |
+
4096,
|
1652 |
+
1024
|
1653 |
+
],
|
1654 |
+
"dtype": "float32",
|
1655 |
+
"format": "f32-to-bf16",
|
1656 |
+
"nbytes": 8388608,
|
1657 |
+
"byteOffset": 18876672
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"name": "model.layers.24.self_attn.o_proj.weight",
|
1661 |
+
"shape": [
|
1662 |
+
1024,
|
1663 |
+
2048
|
1664 |
+
],
|
1665 |
+
"dtype": "float32",
|
1666 |
+
"format": "f32-to-bf16",
|
1667 |
+
"nbytes": 4194304,
|
1668 |
+
"byteOffset": 27265280
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"name": "model.layers.24.self_attn.q_norm.weight",
|
1672 |
+
"shape": [
|
1673 |
+
128
|
1674 |
+
],
|
1675 |
+
"dtype": "float32",
|
1676 |
+
"format": "f32-to-bf16",
|
1677 |
+
"nbytes": 256,
|
1678 |
+
"byteOffset": 31459584
|
1679 |
+
},
|
1680 |
+
{
|
1681 |
+
"name": "model.layers.25.input_layernorm.weight",
|
1682 |
+
"shape": [
|
1683 |
+
1024
|
1684 |
+
],
|
1685 |
+
"dtype": "float32",
|
1686 |
+
"format": "f32-to-bf16",
|
1687 |
+
"nbytes": 2048,
|
1688 |
+
"byteOffset": 31459840
|
1689 |
+
}
|
1690 |
+
],
|
1691 |
+
"md5sum": "1d9f848a8eba2d142c9aa2d536969ecf"
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"dataPath": "params_shard_19.bin",
|
1695 |
+
"format": "raw-shard",
|
1696 |
+
"nbytes": 31461888,
|
1697 |
+
"records": [
|
1698 |
+
{
|
1699 |
+
"name": "model.layers.25.mlp.down_proj.weight",
|
1700 |
+
"shape": [
|
1701 |
+
1024,
|
1702 |
+
3072
|
1703 |
+
],
|
1704 |
+
"dtype": "float32",
|
1705 |
+
"format": "f32-to-bf16",
|
1706 |
+
"nbytes": 6291456,
|
1707 |
+
"byteOffset": 0
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"name": "model.layers.25.mlp.gate_up_proj.weight",
|
1711 |
+
"shape": [
|
1712 |
+
6144,
|
1713 |
+
1024
|
1714 |
+
],
|
1715 |
+
"dtype": "float32",
|
1716 |
+
"format": "f32-to-bf16",
|
1717 |
+
"nbytes": 12582912,
|
1718 |
+
"byteOffset": 6291456
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"name": "model.layers.25.post_attention_layernorm.weight",
|
1722 |
+
"shape": [
|
1723 |
+
1024
|
1724 |
+
],
|
1725 |
+
"dtype": "float32",
|
1726 |
+
"format": "f32-to-bf16",
|
1727 |
+
"nbytes": 2048,
|
1728 |
+
"byteOffset": 18874368
|
1729 |
+
},
|
1730 |
+
{
|
1731 |
+
"name": "model.layers.25.self_attn.k_norm.weight",
|
1732 |
+
"shape": [
|
1733 |
+
128
|
1734 |
+
],
|
1735 |
+
"dtype": "float32",
|
1736 |
+
"format": "f32-to-bf16",
|
1737 |
+
"nbytes": 256,
|
1738 |
+
"byteOffset": 18876416
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"name": "model.layers.25.self_attn.c_attn.weight",
|
1742 |
+
"shape": [
|
1743 |
+
4096,
|
1744 |
+
1024
|
1745 |
+
],
|
1746 |
+
"dtype": "float32",
|
1747 |
+
"format": "f32-to-bf16",
|
1748 |
+
"nbytes": 8388608,
|
1749 |
+
"byteOffset": 18876672
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"name": "model.layers.25.self_attn.o_proj.weight",
|
1753 |
+
"shape": [
|
1754 |
+
1024,
|
1755 |
+
2048
|
1756 |
+
],
|
1757 |
+
"dtype": "float32",
|
1758 |
+
"format": "f32-to-bf16",
|
1759 |
+
"nbytes": 4194304,
|
1760 |
+
"byteOffset": 27265280
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"name": "model.layers.25.self_attn.q_norm.weight",
|
1764 |
+
"shape": [
|
1765 |
+
128
|
1766 |
+
],
|
1767 |
+
"dtype": "float32",
|
1768 |
+
"format": "f32-to-bf16",
|
1769 |
+
"nbytes": 256,
|
1770 |
+
"byteOffset": 31459584
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"name": "model.layers.26.input_layernorm.weight",
|
1774 |
+
"shape": [
|
1775 |
+
1024
|
1776 |
+
],
|
1777 |
+
"dtype": "float32",
|
1778 |
+
"format": "f32-to-bf16",
|
1779 |
+
"nbytes": 2048,
|
1780 |
+
"byteOffset": 31459840
|
1781 |
+
}
|
1782 |
+
],
|
1783 |
+
"md5sum": "e6125aaacc98c10d3e7702aa6bdb39d8"
|
1784 |
+
},
|
1785 |
+
{
|
1786 |
+
"dataPath": "params_shard_20.bin",
|
1787 |
+
"format": "raw-shard",
|
1788 |
+
"nbytes": 31461888,
|
1789 |
+
"records": [
|
1790 |
+
{
|
1791 |
+
"name": "model.layers.26.mlp.down_proj.weight",
|
1792 |
+
"shape": [
|
1793 |
+
1024,
|
1794 |
+
3072
|
1795 |
+
],
|
1796 |
+
"dtype": "float32",
|
1797 |
+
"format": "f32-to-bf16",
|
1798 |
+
"nbytes": 6291456,
|
1799 |
+
"byteOffset": 0
|
1800 |
+
},
|
1801 |
+
{
|
1802 |
+
"name": "model.layers.26.mlp.gate_up_proj.weight",
|
1803 |
+
"shape": [
|
1804 |
+
6144,
|
1805 |
+
1024
|
1806 |
+
],
|
1807 |
+
"dtype": "float32",
|
1808 |
+
"format": "f32-to-bf16",
|
1809 |
+
"nbytes": 12582912,
|
1810 |
+
"byteOffset": 6291456
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"name": "model.layers.26.post_attention_layernorm.weight",
|
1814 |
+
"shape": [
|
1815 |
+
1024
|
1816 |
+
],
|
1817 |
+
"dtype": "float32",
|
1818 |
+
"format": "f32-to-bf16",
|
1819 |
+
"nbytes": 2048,
|
1820 |
+
"byteOffset": 18874368
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"name": "model.layers.26.self_attn.k_norm.weight",
|
1824 |
+
"shape": [
|
1825 |
+
128
|
1826 |
+
],
|
1827 |
+
"dtype": "float32",
|
1828 |
+
"format": "f32-to-bf16",
|
1829 |
+
"nbytes": 256,
|
1830 |
+
"byteOffset": 18876416
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"name": "model.layers.26.self_attn.c_attn.weight",
|
1834 |
+
"shape": [
|
1835 |
+
4096,
|
1836 |
+
1024
|
1837 |
+
],
|
1838 |
+
"dtype": "float32",
|
1839 |
+
"format": "f32-to-bf16",
|
1840 |
+
"nbytes": 8388608,
|
1841 |
+
"byteOffset": 18876672
|
1842 |
+
},
|
1843 |
+
{
|
1844 |
+
"name": "model.layers.26.self_attn.o_proj.weight",
|
1845 |
+
"shape": [
|
1846 |
+
1024,
|
1847 |
+
2048
|
1848 |
+
],
|
1849 |
+
"dtype": "float32",
|
1850 |
+
"format": "f32-to-bf16",
|
1851 |
+
"nbytes": 4194304,
|
1852 |
+
"byteOffset": 27265280
|
1853 |
+
},
|
1854 |
+
{
|
1855 |
+
"name": "model.layers.26.self_attn.q_norm.weight",
|
1856 |
+
"shape": [
|
1857 |
+
128
|
1858 |
+
],
|
1859 |
+
"dtype": "float32",
|
1860 |
+
"format": "f32-to-bf16",
|
1861 |
+
"nbytes": 256,
|
1862 |
+
"byteOffset": 31459584
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"name": "model.layers.27.input_layernorm.weight",
|
1866 |
+
"shape": [
|
1867 |
+
1024
|
1868 |
+
],
|
1869 |
+
"dtype": "float32",
|
1870 |
+
"format": "f32-to-bf16",
|
1871 |
+
"nbytes": 2048,
|
1872 |
+
"byteOffset": 31459840
|
1873 |
+
}
|
1874 |
+
],
|
1875 |
+
"md5sum": "9d135333707ef2f4acb7dd7cf9326f25"
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"dataPath": "params_shard_21.bin",
|
1879 |
+
"format": "raw-shard",
|
1880 |
+
"nbytes": 31461888,
|
1881 |
+
"records": [
|
1882 |
+
{
|
1883 |
+
"name": "model.layers.27.mlp.down_proj.weight",
|
1884 |
+
"shape": [
|
1885 |
+
1024,
|
1886 |
+
3072
|
1887 |
+
],
|
1888 |
+
"dtype": "float32",
|
1889 |
+
"format": "f32-to-bf16",
|
1890 |
+
"nbytes": 6291456,
|
1891 |
+
"byteOffset": 0
|
1892 |
+
},
|
1893 |
+
{
|
1894 |
+
"name": "model.layers.27.mlp.gate_up_proj.weight",
|
1895 |
+
"shape": [
|
1896 |
+
6144,
|
1897 |
+
1024
|
1898 |
+
],
|
1899 |
+
"dtype": "float32",
|
1900 |
+
"format": "f32-to-bf16",
|
1901 |
+
"nbytes": 12582912,
|
1902 |
+
"byteOffset": 6291456
|
1903 |
+
},
|
1904 |
+
{
|
1905 |
+
"name": "model.layers.27.post_attention_layernorm.weight",
|
1906 |
+
"shape": [
|
1907 |
+
1024
|
1908 |
+
],
|
1909 |
+
"dtype": "float32",
|
1910 |
+
"format": "f32-to-bf16",
|
1911 |
+
"nbytes": 2048,
|
1912 |
+
"byteOffset": 18874368
|
1913 |
+
},
|
1914 |
+
{
|
1915 |
+
"name": "model.layers.27.self_attn.k_norm.weight",
|
1916 |
+
"shape": [
|
1917 |
+
128
|
1918 |
+
],
|
1919 |
+
"dtype": "float32",
|
1920 |
+
"format": "f32-to-bf16",
|
1921 |
+
"nbytes": 256,
|
1922 |
+
"byteOffset": 18876416
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"name": "model.layers.27.self_attn.c_attn.weight",
|
1926 |
+
"shape": [
|
1927 |
+
4096,
|
1928 |
+
1024
|
1929 |
+
],
|
1930 |
+
"dtype": "float32",
|
1931 |
+
"format": "f32-to-bf16",
|
1932 |
+
"nbytes": 8388608,
|
1933 |
+
"byteOffset": 18876672
|
1934 |
+
},
|
1935 |
+
{
|
1936 |
+
"name": "model.layers.27.self_attn.o_proj.weight",
|
1937 |
+
"shape": [
|
1938 |
+
1024,
|
1939 |
+
2048
|
1940 |
+
],
|
1941 |
+
"dtype": "float32",
|
1942 |
+
"format": "f32-to-bf16",
|
1943 |
+
"nbytes": 4194304,
|
1944 |
+
"byteOffset": 27265280
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"name": "model.layers.27.self_attn.q_norm.weight",
|
1948 |
+
"shape": [
|
1949 |
+
128
|
1950 |
+
],
|
1951 |
+
"dtype": "float32",
|
1952 |
+
"format": "f32-to-bf16",
|
1953 |
+
"nbytes": 256,
|
1954 |
+
"byteOffset": 31459584
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"name": "model.layers.3.input_layernorm.weight",
|
1958 |
+
"shape": [
|
1959 |
+
1024
|
1960 |
+
],
|
1961 |
+
"dtype": "float32",
|
1962 |
+
"format": "f32-to-bf16",
|
1963 |
+
"nbytes": 2048,
|
1964 |
+
"byteOffset": 31459840
|
1965 |
+
}
|
1966 |
+
],
|
1967 |
+
"md5sum": "e07ec46dc1988b87491a60c6e922c02a"
|
1968 |
+
},
|
1969 |
+
{
|
1970 |
+
"dataPath": "params_shard_22.bin",
|
1971 |
+
"format": "raw-shard",
|
1972 |
+
"nbytes": 31461888,
|
1973 |
+
"records": [
|
1974 |
+
{
|
1975 |
+
"name": "model.layers.3.mlp.down_proj.weight",
|
1976 |
+
"shape": [
|
1977 |
+
1024,
|
1978 |
+
3072
|
1979 |
+
],
|
1980 |
+
"dtype": "float32",
|
1981 |
+
"format": "f32-to-bf16",
|
1982 |
+
"nbytes": 6291456,
|
1983 |
+
"byteOffset": 0
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"name": "model.layers.3.mlp.gate_up_proj.weight",
|
1987 |
+
"shape": [
|
1988 |
+
6144,
|
1989 |
+
1024
|
1990 |
+
],
|
1991 |
+
"dtype": "float32",
|
1992 |
+
"format": "f32-to-bf16",
|
1993 |
+
"nbytes": 12582912,
|
1994 |
+
"byteOffset": 6291456
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
1998 |
+
"shape": [
|
1999 |
+
1024
|
2000 |
+
],
|
2001 |
+
"dtype": "float32",
|
2002 |
+
"format": "f32-to-bf16",
|
2003 |
+
"nbytes": 2048,
|
2004 |
+
"byteOffset": 18874368
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"name": "model.layers.3.self_attn.k_norm.weight",
|
2008 |
+
"shape": [
|
2009 |
+
128
|
2010 |
+
],
|
2011 |
+
"dtype": "float32",
|
2012 |
+
"format": "f32-to-bf16",
|
2013 |
+
"nbytes": 256,
|
2014 |
+
"byteOffset": 18876416
|
2015 |
+
},
|
2016 |
+
{
|
2017 |
+
"name": "model.layers.3.self_attn.c_attn.weight",
|
2018 |
+
"shape": [
|
2019 |
+
4096,
|
2020 |
+
1024
|
2021 |
+
],
|
2022 |
+
"dtype": "float32",
|
2023 |
+
"format": "f32-to-bf16",
|
2024 |
+
"nbytes": 8388608,
|
2025 |
+
"byteOffset": 18876672
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"name": "model.layers.3.self_attn.o_proj.weight",
|
2029 |
+
"shape": [
|
2030 |
+
1024,
|
2031 |
+
2048
|
2032 |
+
],
|
2033 |
+
"dtype": "float32",
|
2034 |
+
"format": "f32-to-bf16",
|
2035 |
+
"nbytes": 4194304,
|
2036 |
+
"byteOffset": 27265280
|
2037 |
+
},
|
2038 |
+
{
|
2039 |
+
"name": "model.layers.3.self_attn.q_norm.weight",
|
2040 |
+
"shape": [
|
2041 |
+
128
|
2042 |
+
],
|
2043 |
+
"dtype": "float32",
|
2044 |
+
"format": "f32-to-bf16",
|
2045 |
+
"nbytes": 256,
|
2046 |
+
"byteOffset": 31459584
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"name": "model.layers.4.input_layernorm.weight",
|
2050 |
+
"shape": [
|
2051 |
+
1024
|
2052 |
+
],
|
2053 |
+
"dtype": "float32",
|
2054 |
+
"format": "f32-to-bf16",
|
2055 |
+
"nbytes": 2048,
|
2056 |
+
"byteOffset": 31459840
|
2057 |
+
}
|
2058 |
+
],
|
2059 |
+
"md5sum": "f0b4915b859259222e9787ee1e7b354d"
|
2060 |
+
},
|
2061 |
+
{
|
2062 |
+
"dataPath": "params_shard_23.bin",
|
2063 |
+
"format": "raw-shard",
|
2064 |
+
"nbytes": 31461888,
|
2065 |
+
"records": [
|
2066 |
+
{
|
2067 |
+
"name": "model.layers.4.mlp.down_proj.weight",
|
2068 |
+
"shape": [
|
2069 |
+
1024,
|
2070 |
+
3072
|
2071 |
+
],
|
2072 |
+
"dtype": "float32",
|
2073 |
+
"format": "f32-to-bf16",
|
2074 |
+
"nbytes": 6291456,
|
2075 |
+
"byteOffset": 0
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"name": "model.layers.4.mlp.gate_up_proj.weight",
|
2079 |
+
"shape": [
|
2080 |
+
6144,
|
2081 |
+
1024
|
2082 |
+
],
|
2083 |
+
"dtype": "float32",
|
2084 |
+
"format": "f32-to-bf16",
|
2085 |
+
"nbytes": 12582912,
|
2086 |
+
"byteOffset": 6291456
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
2090 |
+
"shape": [
|
2091 |
+
1024
|
2092 |
+
],
|
2093 |
+
"dtype": "float32",
|
2094 |
+
"format": "f32-to-bf16",
|
2095 |
+
"nbytes": 2048,
|
2096 |
+
"byteOffset": 18874368
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"name": "model.layers.4.self_attn.k_norm.weight",
|
2100 |
+
"shape": [
|
2101 |
+
128
|
2102 |
+
],
|
2103 |
+
"dtype": "float32",
|
2104 |
+
"format": "f32-to-bf16",
|
2105 |
+
"nbytes": 256,
|
2106 |
+
"byteOffset": 18876416
|
2107 |
+
},
|
2108 |
+
{
|
2109 |
+
"name": "model.layers.4.self_attn.c_attn.weight",
|
2110 |
+
"shape": [
|
2111 |
+
4096,
|
2112 |
+
1024
|
2113 |
+
],
|
2114 |
+
"dtype": "float32",
|
2115 |
+
"format": "f32-to-bf16",
|
2116 |
+
"nbytes": 8388608,
|
2117 |
+
"byteOffset": 18876672
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"name": "model.layers.4.self_attn.o_proj.weight",
|
2121 |
+
"shape": [
|
2122 |
+
1024,
|
2123 |
+
2048
|
2124 |
+
],
|
2125 |
+
"dtype": "float32",
|
2126 |
+
"format": "f32-to-bf16",
|
2127 |
+
"nbytes": 4194304,
|
2128 |
+
"byteOffset": 27265280
|
2129 |
+
},
|
2130 |
+
{
|
2131 |
+
"name": "model.layers.4.self_attn.q_norm.weight",
|
2132 |
+
"shape": [
|
2133 |
+
128
|
2134 |
+
],
|
2135 |
+
"dtype": "float32",
|
2136 |
+
"format": "f32-to-bf16",
|
2137 |
+
"nbytes": 256,
|
2138 |
+
"byteOffset": 31459584
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"name": "model.layers.5.input_layernorm.weight",
|
2142 |
+
"shape": [
|
2143 |
+
1024
|
2144 |
+
],
|
2145 |
+
"dtype": "float32",
|
2146 |
+
"format": "f32-to-bf16",
|
2147 |
+
"nbytes": 2048,
|
2148 |
+
"byteOffset": 31459840
|
2149 |
+
}
|
2150 |
+
],
|
2151 |
+
"md5sum": "890c68f7289867143b40975439f97c02"
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"dataPath": "params_shard_24.bin",
|
2155 |
+
"format": "raw-shard",
|
2156 |
+
"nbytes": 31461888,
|
2157 |
+
"records": [
|
2158 |
+
{
|
2159 |
+
"name": "model.layers.5.mlp.down_proj.weight",
|
2160 |
+
"shape": [
|
2161 |
+
1024,
|
2162 |
+
3072
|
2163 |
+
],
|
2164 |
+
"dtype": "float32",
|
2165 |
+
"format": "f32-to-bf16",
|
2166 |
+
"nbytes": 6291456,
|
2167 |
+
"byteOffset": 0
|
2168 |
+
},
|
2169 |
+
{
|
2170 |
+
"name": "model.layers.5.mlp.gate_up_proj.weight",
|
2171 |
+
"shape": [
|
2172 |
+
6144,
|
2173 |
+
1024
|
2174 |
+
],
|
2175 |
+
"dtype": "float32",
|
2176 |
+
"format": "f32-to-bf16",
|
2177 |
+
"nbytes": 12582912,
|
2178 |
+
"byteOffset": 6291456
|
2179 |
+
},
|
2180 |
+
{
|
2181 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
2182 |
+
"shape": [
|
2183 |
+
1024
|
2184 |
+
],
|
2185 |
+
"dtype": "float32",
|
2186 |
+
"format": "f32-to-bf16",
|
2187 |
+
"nbytes": 2048,
|
2188 |
+
"byteOffset": 18874368
|
2189 |
+
},
|
2190 |
+
{
|
2191 |
+
"name": "model.layers.5.self_attn.k_norm.weight",
|
2192 |
+
"shape": [
|
2193 |
+
128
|
2194 |
+
],
|
2195 |
+
"dtype": "float32",
|
2196 |
+
"format": "f32-to-bf16",
|
2197 |
+
"nbytes": 256,
|
2198 |
+
"byteOffset": 18876416
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"name": "model.layers.5.self_attn.c_attn.weight",
|
2202 |
+
"shape": [
|
2203 |
+
4096,
|
2204 |
+
1024
|
2205 |
+
],
|
2206 |
+
"dtype": "float32",
|
2207 |
+
"format": "f32-to-bf16",
|
2208 |
+
"nbytes": 8388608,
|
2209 |
+
"byteOffset": 18876672
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"name": "model.layers.5.self_attn.o_proj.weight",
|
2213 |
+
"shape": [
|
2214 |
+
1024,
|
2215 |
+
2048
|
2216 |
+
],
|
2217 |
+
"dtype": "float32",
|
2218 |
+
"format": "f32-to-bf16",
|
2219 |
+
"nbytes": 4194304,
|
2220 |
+
"byteOffset": 27265280
|
2221 |
+
},
|
2222 |
+
{
|
2223 |
+
"name": "model.layers.5.self_attn.q_norm.weight",
|
2224 |
+
"shape": [
|
2225 |
+
128
|
2226 |
+
],
|
2227 |
+
"dtype": "float32",
|
2228 |
+
"format": "f32-to-bf16",
|
2229 |
+
"nbytes": 256,
|
2230 |
+
"byteOffset": 31459584
|
2231 |
+
},
|
2232 |
+
{
|
2233 |
+
"name": "model.layers.6.input_layernorm.weight",
|
2234 |
+
"shape": [
|
2235 |
+
1024
|
2236 |
+
],
|
2237 |
+
"dtype": "float32",
|
2238 |
+
"format": "f32-to-bf16",
|
2239 |
+
"nbytes": 2048,
|
2240 |
+
"byteOffset": 31459840
|
2241 |
+
}
|
2242 |
+
],
|
2243 |
+
"md5sum": "4a2e6abf9a0ac27fed499bb02f61047b"
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"dataPath": "params_shard_25.bin",
|
2247 |
+
"format": "raw-shard",
|
2248 |
+
"nbytes": 31461888,
|
2249 |
+
"records": [
|
2250 |
+
{
|
2251 |
+
"name": "model.layers.6.mlp.down_proj.weight",
|
2252 |
+
"shape": [
|
2253 |
+
1024,
|
2254 |
+
3072
|
2255 |
+
],
|
2256 |
+
"dtype": "float32",
|
2257 |
+
"format": "f32-to-bf16",
|
2258 |
+
"nbytes": 6291456,
|
2259 |
+
"byteOffset": 0
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"name": "model.layers.6.mlp.gate_up_proj.weight",
|
2263 |
+
"shape": [
|
2264 |
+
6144,
|
2265 |
+
1024
|
2266 |
+
],
|
2267 |
+
"dtype": "float32",
|
2268 |
+
"format": "f32-to-bf16",
|
2269 |
+
"nbytes": 12582912,
|
2270 |
+
"byteOffset": 6291456
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
2274 |
+
"shape": [
|
2275 |
+
1024
|
2276 |
+
],
|
2277 |
+
"dtype": "float32",
|
2278 |
+
"format": "f32-to-bf16",
|
2279 |
+
"nbytes": 2048,
|
2280 |
+
"byteOffset": 18874368
|
2281 |
+
},
|
2282 |
+
{
|
2283 |
+
"name": "model.layers.6.self_attn.k_norm.weight",
|
2284 |
+
"shape": [
|
2285 |
+
128
|
2286 |
+
],
|
2287 |
+
"dtype": "float32",
|
2288 |
+
"format": "f32-to-bf16",
|
2289 |
+
"nbytes": 256,
|
2290 |
+
"byteOffset": 18876416
|
2291 |
+
},
|
2292 |
+
{
|
2293 |
+
"name": "model.layers.6.self_attn.c_attn.weight",
|
2294 |
+
"shape": [
|
2295 |
+
4096,
|
2296 |
+
1024
|
2297 |
+
],
|
2298 |
+
"dtype": "float32",
|
2299 |
+
"format": "f32-to-bf16",
|
2300 |
+
"nbytes": 8388608,
|
2301 |
+
"byteOffset": 18876672
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"name": "model.layers.6.self_attn.o_proj.weight",
|
2305 |
+
"shape": [
|
2306 |
+
1024,
|
2307 |
+
2048
|
2308 |
+
],
|
2309 |
+
"dtype": "float32",
|
2310 |
+
"format": "f32-to-bf16",
|
2311 |
+
"nbytes": 4194304,
|
2312 |
+
"byteOffset": 27265280
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"name": "model.layers.6.self_attn.q_norm.weight",
|
2316 |
+
"shape": [
|
2317 |
+
128
|
2318 |
+
],
|
2319 |
+
"dtype": "float32",
|
2320 |
+
"format": "f32-to-bf16",
|
2321 |
+
"nbytes": 256,
|
2322 |
+
"byteOffset": 31459584
|
2323 |
+
},
|
2324 |
+
{
|
2325 |
+
"name": "model.layers.7.input_layernorm.weight",
|
2326 |
+
"shape": [
|
2327 |
+
1024
|
2328 |
+
],
|
2329 |
+
"dtype": "float32",
|
2330 |
+
"format": "f32-to-bf16",
|
2331 |
+
"nbytes": 2048,
|
2332 |
+
"byteOffset": 31459840
|
2333 |
+
}
|
2334 |
+
],
|
2335 |
+
"md5sum": "bbf21bdcb33c7b1dfaf7279672693cc2"
|
2336 |
+
},
|
2337 |
+
{
|
2338 |
+
"dataPath": "params_shard_26.bin",
|
2339 |
+
"format": "raw-shard",
|
2340 |
+
"nbytes": 31461888,
|
2341 |
+
"records": [
|
2342 |
+
{
|
2343 |
+
"name": "model.layers.7.mlp.down_proj.weight",
|
2344 |
+
"shape": [
|
2345 |
+
1024,
|
2346 |
+
3072
|
2347 |
+
],
|
2348 |
+
"dtype": "float32",
|
2349 |
+
"format": "f32-to-bf16",
|
2350 |
+
"nbytes": 6291456,
|
2351 |
+
"byteOffset": 0
|
2352 |
+
},
|
2353 |
+
{
|
2354 |
+
"name": "model.layers.7.mlp.gate_up_proj.weight",
|
2355 |
+
"shape": [
|
2356 |
+
6144,
|
2357 |
+
1024
|
2358 |
+
],
|
2359 |
+
"dtype": "float32",
|
2360 |
+
"format": "f32-to-bf16",
|
2361 |
+
"nbytes": 12582912,
|
2362 |
+
"byteOffset": 6291456
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
2366 |
+
"shape": [
|
2367 |
+
1024
|
2368 |
+
],
|
2369 |
+
"dtype": "float32",
|
2370 |
+
"format": "f32-to-bf16",
|
2371 |
+
"nbytes": 2048,
|
2372 |
+
"byteOffset": 18874368
|
2373 |
+
},
|
2374 |
+
{
|
2375 |
+
"name": "model.layers.7.self_attn.k_norm.weight",
|
2376 |
+
"shape": [
|
2377 |
+
128
|
2378 |
+
],
|
2379 |
+
"dtype": "float32",
|
2380 |
+
"format": "f32-to-bf16",
|
2381 |
+
"nbytes": 256,
|
2382 |
+
"byteOffset": 18876416
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"name": "model.layers.7.self_attn.c_attn.weight",
|
2386 |
+
"shape": [
|
2387 |
+
4096,
|
2388 |
+
1024
|
2389 |
+
],
|
2390 |
+
"dtype": "float32",
|
2391 |
+
"format": "f32-to-bf16",
|
2392 |
+
"nbytes": 8388608,
|
2393 |
+
"byteOffset": 18876672
|
2394 |
+
},
|
2395 |
+
{
|
2396 |
+
"name": "model.layers.7.self_attn.o_proj.weight",
|
2397 |
+
"shape": [
|
2398 |
+
1024,
|
2399 |
+
2048
|
2400 |
+
],
|
2401 |
+
"dtype": "float32",
|
2402 |
+
"format": "f32-to-bf16",
|
2403 |
+
"nbytes": 4194304,
|
2404 |
+
"byteOffset": 27265280
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"name": "model.layers.7.self_attn.q_norm.weight",
|
2408 |
+
"shape": [
|
2409 |
+
128
|
2410 |
+
],
|
2411 |
+
"dtype": "float32",
|
2412 |
+
"format": "f32-to-bf16",
|
2413 |
+
"nbytes": 256,
|
2414 |
+
"byteOffset": 31459584
|
2415 |
+
},
|
2416 |
+
{
|
2417 |
+
"name": "model.layers.8.input_layernorm.weight",
|
2418 |
+
"shape": [
|
2419 |
+
1024
|
2420 |
+
],
|
2421 |
+
"dtype": "float32",
|
2422 |
+
"format": "f32-to-bf16",
|
2423 |
+
"nbytes": 2048,
|
2424 |
+
"byteOffset": 31459840
|
2425 |
+
}
|
2426 |
+
],
|
2427 |
+
"md5sum": "d0db88ea1fdab01e768d9ee5a4cc24e1"
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"dataPath": "params_shard_27.bin",
|
2431 |
+
"format": "raw-shard",
|
2432 |
+
"nbytes": 31461888,
|
2433 |
+
"records": [
|
2434 |
+
{
|
2435 |
+
"name": "model.layers.8.mlp.down_proj.weight",
|
2436 |
+
"shape": [
|
2437 |
+
1024,
|
2438 |
+
3072
|
2439 |
+
],
|
2440 |
+
"dtype": "float32",
|
2441 |
+
"format": "f32-to-bf16",
|
2442 |
+
"nbytes": 6291456,
|
2443 |
+
"byteOffset": 0
|
2444 |
+
},
|
2445 |
+
{
|
2446 |
+
"name": "model.layers.8.mlp.gate_up_proj.weight",
|
2447 |
+
"shape": [
|
2448 |
+
6144,
|
2449 |
+
1024
|
2450 |
+
],
|
2451 |
+
"dtype": "float32",
|
2452 |
+
"format": "f32-to-bf16",
|
2453 |
+
"nbytes": 12582912,
|
2454 |
+
"byteOffset": 6291456
|
2455 |
+
},
|
2456 |
+
{
|
2457 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
2458 |
+
"shape": [
|
2459 |
+
1024
|
2460 |
+
],
|
2461 |
+
"dtype": "float32",
|
2462 |
+
"format": "f32-to-bf16",
|
2463 |
+
"nbytes": 2048,
|
2464 |
+
"byteOffset": 18874368
|
2465 |
+
},
|
2466 |
+
{
|
2467 |
+
"name": "model.layers.8.self_attn.k_norm.weight",
|
2468 |
+
"shape": [
|
2469 |
+
128
|
2470 |
+
],
|
2471 |
+
"dtype": "float32",
|
2472 |
+
"format": "f32-to-bf16",
|
2473 |
+
"nbytes": 256,
|
2474 |
+
"byteOffset": 18876416
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"name": "model.layers.8.self_attn.c_attn.weight",
|
2478 |
+
"shape": [
|
2479 |
+
4096,
|
2480 |
+
1024
|
2481 |
+
],
|
2482 |
+
"dtype": "float32",
|
2483 |
+
"format": "f32-to-bf16",
|
2484 |
+
"nbytes": 8388608,
|
2485 |
+
"byteOffset": 18876672
|
2486 |
+
},
|
2487 |
+
{
|
2488 |
+
"name": "model.layers.8.self_attn.o_proj.weight",
|
2489 |
+
"shape": [
|
2490 |
+
1024,
|
2491 |
+
2048
|
2492 |
+
],
|
2493 |
+
"dtype": "float32",
|
2494 |
+
"format": "f32-to-bf16",
|
2495 |
+
"nbytes": 4194304,
|
2496 |
+
"byteOffset": 27265280
|
2497 |
+
},
|
2498 |
+
{
|
2499 |
+
"name": "model.layers.8.self_attn.q_norm.weight",
|
2500 |
+
"shape": [
|
2501 |
+
128
|
2502 |
+
],
|
2503 |
+
"dtype": "float32",
|
2504 |
+
"format": "f32-to-bf16",
|
2505 |
+
"nbytes": 256,
|
2506 |
+
"byteOffset": 31459584
|
2507 |
+
},
|
2508 |
+
{
|
2509 |
+
"name": "model.layers.9.input_layernorm.weight",
|
2510 |
+
"shape": [
|
2511 |
+
1024
|
2512 |
+
],
|
2513 |
+
"dtype": "float32",
|
2514 |
+
"format": "f32-to-bf16",
|
2515 |
+
"nbytes": 2048,
|
2516 |
+
"byteOffset": 31459840
|
2517 |
+
}
|
2518 |
+
],
|
2519 |
+
"md5sum": "3a05a1acf71722e4ad3b000b324a8649"
|
2520 |
+
},
|
2521 |
+
{
|
2522 |
+
"dataPath": "params_shard_28.bin",
|
2523 |
+
"format": "raw-shard",
|
2524 |
+
"nbytes": 31461888,
|
2525 |
+
"records": [
|
2526 |
+
{
|
2527 |
+
"name": "model.layers.9.mlp.down_proj.weight",
|
2528 |
+
"shape": [
|
2529 |
+
1024,
|
2530 |
+
3072
|
2531 |
+
],
|
2532 |
+
"dtype": "float32",
|
2533 |
+
"format": "f32-to-bf16",
|
2534 |
+
"nbytes": 6291456,
|
2535 |
+
"byteOffset": 0
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"name": "model.layers.9.mlp.gate_up_proj.weight",
|
2539 |
+
"shape": [
|
2540 |
+
6144,
|
2541 |
+
1024
|
2542 |
+
],
|
2543 |
+
"dtype": "float32",
|
2544 |
+
"format": "f32-to-bf16",
|
2545 |
+
"nbytes": 12582912,
|
2546 |
+
"byteOffset": 6291456
|
2547 |
+
},
|
2548 |
+
{
|
2549 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
2550 |
+
"shape": [
|
2551 |
+
1024
|
2552 |
+
],
|
2553 |
+
"dtype": "float32",
|
2554 |
+
"format": "f32-to-bf16",
|
2555 |
+
"nbytes": 2048,
|
2556 |
+
"byteOffset": 18874368
|
2557 |
+
},
|
2558 |
+
{
|
2559 |
+
"name": "model.layers.9.self_attn.k_norm.weight",
|
2560 |
+
"shape": [
|
2561 |
+
128
|
2562 |
+
],
|
2563 |
+
"dtype": "float32",
|
2564 |
+
"format": "f32-to-bf16",
|
2565 |
+
"nbytes": 256,
|
2566 |
+
"byteOffset": 18876416
|
2567 |
+
},
|
2568 |
+
{
|
2569 |
+
"name": "model.layers.9.self_attn.c_attn.weight",
|
2570 |
+
"shape": [
|
2571 |
+
4096,
|
2572 |
+
1024
|
2573 |
+
],
|
2574 |
+
"dtype": "float32",
|
2575 |
+
"format": "f32-to-bf16",
|
2576 |
+
"nbytes": 8388608,
|
2577 |
+
"byteOffset": 18876672
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"name": "model.layers.9.self_attn.o_proj.weight",
|
2581 |
+
"shape": [
|
2582 |
+
1024,
|
2583 |
+
2048
|
2584 |
+
],
|
2585 |
+
"dtype": "float32",
|
2586 |
+
"format": "f32-to-bf16",
|
2587 |
+
"nbytes": 4194304,
|
2588 |
+
"byteOffset": 27265280
|
2589 |
+
},
|
2590 |
+
{
|
2591 |
+
"name": "model.layers.9.self_attn.q_norm.weight",
|
2592 |
+
"shape": [
|
2593 |
+
128
|
2594 |
+
],
|
2595 |
+
"dtype": "float32",
|
2596 |
+
"format": "f32-to-bf16",
|
2597 |
+
"nbytes": 256,
|
2598 |
+
"byteOffset": 31459584
|
2599 |
+
},
|
2600 |
+
{
|
2601 |
+
"name": "model.norm.weight",
|
2602 |
+
"shape": [
|
2603 |
+
1024
|
2604 |
+
],
|
2605 |
+
"dtype": "float32",
|
2606 |
+
"format": "f32-to-bf16",
|
2607 |
+
"nbytes": 2048,
|
2608 |
+
"byteOffset": 31459840
|
2609 |
+
}
|
2610 |
+
],
|
2611 |
+
"md5sum": "195d11d45fdbd6e214234ed298ed0684"
|
2612 |
+
}
|
2613 |
+
]
|
2614 |
+
}
|
params_shard_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f29acf519434862d95613b2b4f6b9d14933a5e4d16baebf8ac0b33b410acfb6
|
3 |
+
size 311164928
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83233c1b455dc0e36429411f083d6f38e124e7e58cd3cc4436430384314e3785
|
3 |
+
size 31463936
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d46238375595a7f76565bdee18731ea6031f921285ef4175c874d2c555198fa
|
3 |
+
size 31461888
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b25e0e839da541c657822508d036b1da3b6a1913dd5338c4fe11a536ed1ea9b9
|
3 |
+
size 31461888
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab32a220d6f2a6a42c370b6bf2565ef6f1bf6a5c51b8424ef4d19325d7399830
|
3 |
+
size 31461888
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b457e2caf9cee635946cd1b582840404a5671296c3e8fa3c729bf51f34ed49f5
|
3 |
+
size 31461888
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9cc626a7849d73934ab0edf64a94c4cbf5b2e7d3cbd46ba89ffc22c0b96217c
|
3 |
+
size 31461888
|
params_shard_15.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49d6b6ce2642cf2320499d227c8a6a853d638a417d694516ea27511c261517fa
|
3 |
+
size 31461888
|
params_shard_16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37cd57a9f8ab682973bac0a50be1592e08fa0d908382dedb60b3052bf6f85a74
|
3 |
+
size 31461888
|
params_shard_17.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9904b7eff91c0dccf6441b701d9e4191a8ab28d1e44724ce7cb994caae1f1c88
|
3 |
+
size 31461888
|
params_shard_18.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9c958f5c1aacaeef99ae7b209b95bf3324d7fb321b49e3c8fa3c32dc3b8b67c
|
3 |
+
size 31461888
|
params_shard_19.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cee4cd069eea253b55db5c1e535f78f1be980023f36f48947702a202b3c09df8
|
3 |
+
size 31461888
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f24490f63c81855bbfb9ff2e5e0048ce09b8ddd920ca77943373b827e45a09d
|
3 |
+
size 31461888
|
params_shard_20.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1dda13b5bcec9840a31dc7abb3582634dacbe74db06f983bf432bccbf245be2
|
3 |
+
size 31461888
|
params_shard_21.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a926f3dbcd9e932a0033178e7dafe66e9d228fc4cb33c25e498b37fb816391f4
|
3 |
+
size 31461888
|
params_shard_22.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afb0d211337d60e78f0bea4d349b8cfaa7ceea823f9cee4a70c25516183b6c50
|
3 |
+
size 31461888
|
params_shard_23.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5140fcdbf253e64a2dbe06d0251fb997b99005a00f8d19f6d4ee3886dfc74a30
|
3 |
+
size 31461888
|
params_shard_24.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d63037f1b3a041f4fbce9111a15c268bb09ca799fadfc318f1c8ed30db8c9ef1
|
3 |
+
size 31461888
|
params_shard_25.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02846856321c4e2d8223a7789588920db249eab99154d7dbfb906bf5f36221f2
|
3 |
+
size 31461888
|
params_shard_26.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39e3051af3273a68591adcfdb8f2aa977700a5917d1d418ff2dce3ca96a57114
|
3 |
+
size 31461888
|
params_shard_27.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0e033e67370325024a1b07d16e583c5b09f864b0f1658c34765b96cd345e994
|
3 |
+
size 31461888
|
params_shard_28.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:805038254db61b39a0e6a05180168fbf369b30d3f1590151d928477b7d989106
|
3 |
+
size 31461888
|
params_shard_3.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23194f922c092e5b83cdaf3138dff240ac04af03d04c3093a6c9ef3500f53b0d
|
3 |
+
size 31461888
|
params_shard_4.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d8d07536a9adc381c13b8ef4ce9ba294b475ab62b9c254c5e00bbe2795f9509
|
3 |
+
size 31461888
|
params_shard_5.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eff5f43af8357851054b54776b953c0af3e67ee8aeb90ed9d911c578fb5facfb
|
3 |
+
size 31461888
|
params_shard_6.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f99d42a1ab0aae875342f066edc5b2c6d13688b783c85090f6076976b1f61982
|
3 |
+
size 31461888
|
params_shard_7.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf9e34dd5021363c0378bd22c50051526e373540828751ec5a8768e8d4b50706
|
3 |
+
size 31461888
|
params_shard_8.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29f2eba9f5ac79fa2d1559f424a13148cd1fa07e064a7e7096ee706be8ce50d6
|
3 |
+
size 31461888
|
params_shard_9.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de9a02593a91d671810796b2d02063b6eb0795a7ca792fb46d134a26364d1460
|
3 |
+
size 31461888
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
3 |
+
size 11422654
|
tokenizer_config.json
ADDED
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
},
|
181 |
+
"151665": {
|
182 |
+
"content": "<tool_response>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"151666": {
|
190 |
+
"content": "</tool_response>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"151667": {
|
198 |
+
"content": "<think>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": false
|
204 |
+
},
|
205 |
+
"151668": {
|
206 |
+
"content": "</think>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": false
|
212 |
+
}
|
213 |
+
},
|
214 |
+
"additional_special_tokens": [
|
215 |
+
"<|im_start|>",
|
216 |
+
"<|im_end|>",
|
217 |
+
"<|object_ref_start|>",
|
218 |
+
"<|object_ref_end|>",
|
219 |
+
"<|box_start|>",
|
220 |
+
"<|box_end|>",
|
221 |
+
"<|quad_start|>",
|
222 |
+
"<|quad_end|>",
|
223 |
+
"<|vision_start|>",
|
224 |
+
"<|vision_end|>",
|
225 |
+
"<|vision_pad|>",
|
226 |
+
"<|image_pad|>",
|
227 |
+
"<|video_pad|>"
|
228 |
+
],
|
229 |
+
"bos_token": null,
|
230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
231 |
+
"clean_up_tokenization_spaces": false,
|
232 |
+
"eos_token": "<|im_end|>",
|
233 |
+
"errors": "replace",
|
234 |
+
"model_max_length": 131072,
|
235 |
+
"pad_token": "<|endoftext|>",
|
236 |
+
"split_special_tokens": false,
|
237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
238 |
+
"unk_token": null
|
239 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|