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-b16.json +0 -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
.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": "q4f32_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-b16.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 sha256:4f58a9e1cb2a9a805ccc85cc9a462a7e66fb0b71b96ec5652e382be3840b1682
|
3 |
+
size 311164928
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf72970db670836c306e742aa00ed104e4f121aca8518f167627b8506312e0f5
|
3 |
+
size 38895616
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4de50cab21e3f9c239d72eebc58a460f72b298c26eb5ca7deda3845009d901e4
|
3 |
+
size 805306368
|
params_shard_100.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:376541e3935ed357a53dbde77489a2da21bdd9c8b1824fb474712a217934fcb7
|
3 |
+
size 33342976
|
params_shard_101.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df0d8ef8f1959fd1af7b78eb389c0715ffb63774d988b8b7520fe66443478593
|
3 |
+
size 402653184
|
params_shard_102.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99ef4e3eb96c3b93a518ddc0ed9aefbf120ecc3195e474d71deac430014c52e1
|
3 |
+
size 50331648
|
params_shard_103.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8496f09df7267aa147bd2860dc2a95f62845402ea8015038610ce8f400ea632e
|
3 |
+
size 805306368
|
params_shard_104.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66877617585144a2a28a997691fc5164dd9fafb18ee5aa372e5268e83321086b
|
3 |
+
size 100663296
|
params_shard_105.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e53b9f98af8ce48648cf9fb523ff5cd44f76385e21ca107767abb986577ea78
|
3 |
+
size 18874368
|
params_shard_106.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00538216af54119dfa12c264e360f4a2902d3a9d4d5f884c85f7ee22a1e551ce
|
3 |
+
size 16777216
|
params_shard_107.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86aef0b89103c4c9fb5c60cc5d797d33270494a5ee0684fe734e1ec4c887d940
|
3 |
+
size 402653184
|
params_shard_108.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05312f6e79d480bf87427c2db447c416a1b78a1b043332524077fa396b0d83c1
|
3 |
+
size 50331648
|
params_shard_109.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96316eaf6283d47ec9d9234bcaf164ec4022b76f423c2bc35d402965d55233a8
|
3 |
+
size 805306368
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05307ec663b7c7c36799c6ff0feaf6297d05fb18f5ef52da3a3bbc66d8b18732
|
3 |
+
size 100663296
|
params_shard_110.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45999001324a8d4eea8c376c920eed9fb4b7ba5af82b2325e396d96681625dd8
|
3 |
+
size 100663296
|
params_shard_111.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76e1f1bf9b912a98c949acf8f5294ee577e6e43f852a80c75a1d948d8c19e8a8
|
3 |
+
size 18874368
|
params_shard_112.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ef8756c0fdad5b574f6c346589cec329a1b026042c5039198d576dd87db0fe3
|
3 |
+
size 16777216
|
params_shard_113.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7136dc51577d52a668a69c3c99d326ed56bc36afbc1aeb97642c1be7fd753b6
|
3 |
+
size 18874368
|
params_shard_114.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3449ae0f4bda46b0a07fc2caced445a295abc05e3637ab7541d8cea53391d280
|
3 |
+
size 32294144
|
params_shard_115.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b14ed935a80e2a0cf11c82814a89c6d665dd1f69ae8bc329a6058ad975b8b37
|
3 |
+
size 402653184
|
params_shard_116.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af6cb42c7606a9589a589be3003a614b1aebad238eb430c1594bb2039916b3ec
|
3 |
+
size 50331648
|
params_shard_117.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f7e776d1934914f95aac73a66f95586febcd2b0247fd456014f78c4ba3d9be1
|
3 |
+
size 805306368
|
params_shard_118.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8f7338a02a24d48b20ff5bde435685ed4f3b7cacb87dae8e74b2931f34d2666
|
3 |
+
size 100663296
|
params_shard_119.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34101e61b3d0f2222d2f7ff45f5fb89679103b89d972361fc4cf0a9f405a5c22
|
3 |
+
size 402653184
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28fdad247bd0598469a7aa07d9492508a1e3088945eefd5677395835bce6d0ee
|
3 |
+
size 16777216
|
params_shard_120.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:719148c4a42fa184707c4734376fb4fe055ff20a09a02c4d76927d9c1b8ff90e
|
3 |
+
size 50331648
|
params_shard_121.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e832cdf249ccbf5e95da3517b11ad86670077e6603c89def104566c4a911c6bc
|
3 |
+
size 805306368
|
params_shard_122.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:521225e793d5f6eb2898025407b07cf47a819f99ef8eea2d8b6dc4ce70369baf
|
3 |
+
size 100663296
|
params_shard_123.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a28c63b7880707d6dc76af3aadc36bd019bd5145ea00e9487d6ac1a9cfe4361
|
3 |
+
size 16777216
|
params_shard_124.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a646b18d9116308b07a8813cd2737ff8879d294584ec74b4db26a5914fe2a488
|
3 |
+
size 16777216
|
params_shard_125.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0beaaeb166538d44c8f51267fa42a8789a3458902c728a882267605e6d7c9693
|
3 |
+
size 402653184
|
params_shard_126.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae82493c181ab3835278f3d91e6bc392e77717a468f7216ed29620367e8fa323
|
3 |
+
size 50331648
|
params_shard_127.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2baf7a9cbed5b9f59e54a509ee9591239c0f85f54fa8b40c4e468f48354697c3
|
3 |
+
size 805306368
|
params_shard_128.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:995189b2579bf19502166104a57bcc9defe00fbfe15b8d892c8b1ba040ec3f8e
|
3 |
+
size 100663296
|
params_shard_129.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc10b9d186037258379ed23ae737cd7360d7d108a801b88ac6697d0ead6cfeea
|
3 |
+
size 18874368
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04a4d3967c28019abd5acd778b490d9831cd9fcbb61835bfa5cc2051ca4e0442
|
3 |
+
size 402653184
|
params_shard_130.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21794ffe527455a135cd322c3cfcc58ee1eb28f4ec1f1ba5127679bc2151aa23
|
3 |
+
size 16777216
|
params_shard_131.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e1cc31dfa031eb7c0a8410f429d5d4f0c94cfbf84fc0e9653dd8dfea7d9a240
|
3 |
+
size 33326336
|
params_shard_132.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:771d69fda185b92b01ec3cdcc0cc292753f087052da621fadcdfc132cfea6f50
|
3 |
+
size 402653184
|
params_shard_133.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:773459e582d0aff91b88a2b6623489593daad4913eaae9e515be562d04745778
|
3 |
+
size 50331648
|
params_shard_134.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f1591629885d22773d4c8ab6ff016563f0ec81bdb6408778cdfa87ff408b755
|
3 |
+
size 805306368
|
params_shard_135.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b8e0035025f16c1d751c83f6d2f4eec76bba467c11ee3420017dd93e94173b6
|
3 |
+
size 100663296
|
params_shard_136.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8217d2bd598a59ee171009de8262d72182963a1dd229e30afc270c229926a245
|
3 |
+
size 16777216
|
params_shard_137.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92191ce9566bf1e1843ecbf12138cc2359df0bee6892cfc811d24a0f340cfd33
|
3 |
+
size 18874368
|
params_shard_138.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64c076bb0838ccc8c3cb80d7659495f0ddca37f5cbc3a4bf98847eddbfdd0132
|
3 |
+
size 16777216
|