Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- merges.txt +0 -0
- mlc-chat-config.json +91 -0
- ndarray-cache.json +0 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_100.bin +3 -0
- params_shard_101.bin +3 -0
- params_shard_102.bin +3 -0
- params_shard_103.bin +3 -0
- params_shard_104.bin +3 -0
- params_shard_105.bin +3 -0
- params_shard_106.bin +3 -0
- params_shard_107.bin +3 -0
- params_shard_108.bin +3 -0
- params_shard_109.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_110.bin +3 -0
- params_shard_111.bin +3 -0
- params_shard_112.bin +3 -0
- params_shard_113.bin +3 -0
- params_shard_114.bin +3 -0
- params_shard_115.bin +3 -0
- params_shard_116.bin +3 -0
- params_shard_117.bin +3 -0
- params_shard_118.bin +3 -0
- params_shard_119.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_120.bin +3 -0
- params_shard_121.bin +3 -0
- params_shard_122.bin +3 -0
- params_shard_123.bin +3 -0
- params_shard_124.bin +3 -0
- params_shard_125.bin +3 -0
- params_shard_126.bin +3 -0
- params_shard_127.bin +3 -0
- params_shard_128.bin +3 -0
- params_shard_129.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_130.bin +3 -0
- params_shard_131.bin +3 -0
- params_shard_132.bin +3 -0
- params_shard_133.bin +3 -0
- params_shard_134.bin +3 -0
- params_shard_135.bin +3 -0
- params_shard_136.bin +3 -0
- params_shard_137.bin +3 -0
- params_shard_138.bin +3 -0
- params_shard_139.bin +3 -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 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "qwen3_moe",
|
4 |
+
"quantization": "q4f16_1",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_act": "silu",
|
7 |
+
"hidden_size": 4096,
|
8 |
+
"intermediate_size": 12288,
|
9 |
+
"attention_bias": false,
|
10 |
+
"num_attention_heads": 64,
|
11 |
+
"num_hidden_layers": 94,
|
12 |
+
"num_key_value_heads": 4,
|
13 |
+
"rms_norm_eps": 1e-06,
|
14 |
+
"rope_theta": 1000000.0,
|
15 |
+
"vocab_size": 151936,
|
16 |
+
"tie_word_embeddings": false,
|
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 |
+
"moe_intermediate_size": 1536,
|
25 |
+
"num_experts_per_tok": 8,
|
26 |
+
"num_experts": 128,
|
27 |
+
"decoder_sparse_step": 1,
|
28 |
+
"norm_topk_prob": true
|
29 |
+
},
|
30 |
+
"vocab_size": 151936,
|
31 |
+
"context_window_size": 40960,
|
32 |
+
"sliding_window_size": -1,
|
33 |
+
"prefill_chunk_size": 2048,
|
34 |
+
"attention_sink_size": -1,
|
35 |
+
"tensor_parallel_shards": 1,
|
36 |
+
"pipeline_parallel_stages": 1,
|
37 |
+
"temperature": 0.6,
|
38 |
+
"presence_penalty": 0.0,
|
39 |
+
"frequency_penalty": 0.0,
|
40 |
+
"repetition_penalty": 1.0,
|
41 |
+
"top_p": 0.95,
|
42 |
+
"tokenizer_files": [
|
43 |
+
"tokenizer.json",
|
44 |
+
"vocab.json",
|
45 |
+
"merges.txt",
|
46 |
+
"tokenizer_config.json"
|
47 |
+
],
|
48 |
+
"tokenizer_info": {
|
49 |
+
"token_postproc_method": "byte_level",
|
50 |
+
"prepend_space_in_encode": false,
|
51 |
+
"strip_space_in_decode": false
|
52 |
+
},
|
53 |
+
"conv_template": {
|
54 |
+
"name": "qwen2",
|
55 |
+
"system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
|
56 |
+
"system_message": "You are a helpful assistant.",
|
57 |
+
"system_prefix_token_ids": null,
|
58 |
+
"add_role_after_system_message": true,
|
59 |
+
"roles": {
|
60 |
+
"user": "<|im_start|>user",
|
61 |
+
"assistant": "<|im_start|>assistant"
|
62 |
+
},
|
63 |
+
"role_templates": {
|
64 |
+
"user": "{user_message}",
|
65 |
+
"assistant": "{assistant_message}",
|
66 |
+
"tool": "{tool_message}"
|
67 |
+
},
|
68 |
+
"messages": [],
|
69 |
+
"seps": [
|
70 |
+
"<|im_end|>\n"
|
71 |
+
],
|
72 |
+
"role_content_sep": "\n",
|
73 |
+
"role_empty_sep": "\n",
|
74 |
+
"stop_str": [
|
75 |
+
"<|endoftext|>",
|
76 |
+
"<|im_end|>"
|
77 |
+
],
|
78 |
+
"stop_token_ids": [
|
79 |
+
151643,
|
80 |
+
151645
|
81 |
+
],
|
82 |
+
"function_string": "",
|
83 |
+
"use_function_calling": false
|
84 |
+
},
|
85 |
+
"pad_token_id": 151643,
|
86 |
+
"bos_token_id": 151643,
|
87 |
+
"eos_token_id": [
|
88 |
+
151645,
|
89 |
+
151643
|
90 |
+
]
|
91 |
+
}
|
ndarray-cache.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
params_shard_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61e5fb1c93c1d1f8bb43150624db2daaaaa3ff9dda5b0b45bce1c57e5c92b075
|
3 |
+
size 311164928
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60ed633be74643f7651025f4ee9be9d5fd084eb80799122fbc52e41cfd3b805e
|
3 |
+
size 38895616
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8716e7be013d96e8fb4d3f7cba9871b92921473a9c905e29443266bd279690c4
|
3 |
+
size 805306368
|
params_shard_100.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50fc247750cea3fc255f753cfa9d41297f84a2e608408798eceefc8d04c5e62c
|
3 |
+
size 33342976
|
params_shard_101.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85fe82022eeb631819674dafc1f6f57915f6441b5bd8e76c33629f0753104788
|
3 |
+
size 402653184
|
params_shard_102.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5da91790a041613f5335208190085913281e43692beac488d4ac8cfc0164f1fb
|
3 |
+
size 50331648
|
params_shard_103.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:322a9e147f365be8792ccebd922c9229f64ed91f1e37d2c8c58e3e97861b6e1a
|
3 |
+
size 805306368
|
params_shard_104.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79d80905ebd70c702230fe207943b26abaff77a2d6c42d64361bed01912bf6e8
|
3 |
+
size 100663296
|
params_shard_105.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82a47123c8182771ff5881cd95597a508e749a978cd17f659c526919d86beb3e
|
3 |
+
size 18874368
|
params_shard_106.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f43d14ee8688246f58e648ce034c55f3cedb38ffbe9f296e78e9f588b1b53da
|
3 |
+
size 16777216
|
params_shard_107.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0436720f90c8152a63d231a4866e142f0e0f30668d935c850720197b82864a8e
|
3 |
+
size 402653184
|
params_shard_108.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d310ad91eb23574ae3a21726dd8b4e76475139e2a6087196f9cabb1eade08d4
|
3 |
+
size 50331648
|
params_shard_109.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d542d265af1f881e6a469b446fb01b737df6cf6c9629e13c3ab805533bb58def
|
3 |
+
size 805306368
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dab89a69aa4ff327db648fa10c4680dbb068884ef015e78a3d14764480e4169d
|
3 |
+
size 100663296
|
params_shard_110.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bcb293fbd320ff01d761cad16db6ac4c38aca3636a1faa76a6019c85b26eefa
|
3 |
+
size 100663296
|
params_shard_111.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1423beec91d1fc42268cf5ba8dd89877bea51e86aff36404bc463c8c5755b107
|
3 |
+
size 18874368
|
params_shard_112.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cec8a98f172259f3c63e3c8ebc36eb08c497d72b43061eda6c0a992c5dd8a678
|
3 |
+
size 16777216
|
params_shard_113.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36c241d77dd49e6a6183eb7ce9f9cd7c4e532c1798990172ff1b0d7f6832904a
|
3 |
+
size 18874368
|
params_shard_114.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:107200b94209c726714046e3681477618f7e6c3c985825e704c64c2a2857404e
|
3 |
+
size 32294144
|
params_shard_115.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7c213de70618c535bffa78260be29ba0fc857e160010251775965413755f359
|
3 |
+
size 402653184
|
params_shard_116.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f97c931ff1fdc2f85b6442b6f20435f419da98c3a4d65bf68ecd4eef39f850a5
|
3 |
+
size 50331648
|
params_shard_117.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1e7a929049d8766635dccf7268b7fe8b8b0218c681de99f5e1e76f28fdbd4a5
|
3 |
+
size 805306368
|
params_shard_118.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9911c5497d51e2df36c71ae94ac587853a19a15e488e8ee76a67a32a49794e5b
|
3 |
+
size 100663296
|
params_shard_119.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6ec8c0379bfd440043a03ba9918a7e87abc8d0cfc8fa4a861eadfa1573ef25f
|
3 |
+
size 402653184
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2c945b63bd37e62bafb1cc2101bd6581ca90c6393f4cc9095be8d4d5295dc26
|
3 |
+
size 16777216
|
params_shard_120.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77daa449379215e177dc88462de6e13cd261582a3f28b03c7d791bb13cec4e81
|
3 |
+
size 50331648
|
params_shard_121.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3e47dcd3051cb269abd102595edfe5fbf9f223f2a130f11493d18d6fb973518
|
3 |
+
size 805306368
|
params_shard_122.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81ca7ceb4dcbc245065d167878ec200cc3dedde93fb649ab8e8137ac110451db
|
3 |
+
size 100663296
|
params_shard_123.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed15a2a11ead6fbbd46e48fae7df2101e655ad1285cc769ae0558f800ae37f8f
|
3 |
+
size 16777216
|
params_shard_124.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbe1d48b02f30bb2a148d321fe9b911c9934fd2674fce4ae18ca882925b006d1
|
3 |
+
size 16777216
|
params_shard_125.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0344f8b036e44e2fffbbe502cf73ea9981874669b0d42508b27c7a4d1d240c69
|
3 |
+
size 402653184
|
params_shard_126.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dafc1df41aa1c7d5fecd46f7f8c87bb7fcbdd248b0f2e98b7ac146b22ecfa65b
|
3 |
+
size 50331648
|
params_shard_127.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c40ea1a4783ad475841a13dd3649a18f610893a79a92b50f10dbc261b5ea9412
|
3 |
+
size 805306368
|
params_shard_128.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ae6aa684b7fbaba35c1565411114b2085153999e8e79d52efdc16f852011f7c
|
3 |
+
size 100663296
|
params_shard_129.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1947881f12503cceaad7616efdc7da6f6add43045b8234e7ef93df2216295f80
|
3 |
+
size 18874368
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3a26621dfce142495970e4409e286d0cdd9ee3a080affce1976dca3fb0dfea4
|
3 |
+
size 402653184
|
params_shard_130.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbdea8a524d0685995a271330bd8c8764322a02b67a083d295558f4bd834bb88
|
3 |
+
size 16777216
|
params_shard_131.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a05115d1acbc710da95d36ab599eaf8a62e50515da29d6a54cfc4c6282a67841
|
3 |
+
size 33326336
|
params_shard_132.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a24008e63bf0de903ad06981d8bdfc0f5b27c177e4dc76a2479bf0383598473
|
3 |
+
size 402653184
|
params_shard_133.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f842afd4249fb2922b09174f71b43ef4edfba9a6d4cb3ac48ce9402ec910a404
|
3 |
+
size 50331648
|
params_shard_134.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57ec2e464b42883689406115f8e332683bbe19fdd7a1e0a28f096d42d458bd8e
|
3 |
+
size 805306368
|
params_shard_135.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c92706b5fb96d1467c8d1ead74e4aba9ae568a15aeffc15924ac035754782bf5
|
3 |
+
size 100663296
|
params_shard_136.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7a9eca879543d5aca6173fd99cf8b6d66ce1bfddb3328e69a67d6346741d45f
|
3 |
+
size 16777216
|
params_shard_137.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dceb6e1d8ee4451ba0c63a0ce1e48e633df6a727b879966081c9ecd6661d7cd
|
3 |
+
size 18874368
|
params_shard_138.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a912eb0051398293c6658b055caf1d03e86cfc80c7549a6d9cf5bd9c240fa740
|
3 |
+
size 16777216
|
params_shard_139.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eddb7b549cf422fb277b4b58b7f153111bd6d53faa143570d4a3b326f522a66e
|
3 |
+
size 402653184
|