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 +90 -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 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "qwen3_moe",
|
4 |
+
"quantization": "q0f16",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_act": "silu",
|
7 |
+
"hidden_size": 2048,
|
8 |
+
"intermediate_size": 6144,
|
9 |
+
"attention_bias": false,
|
10 |
+
"num_attention_heads": 32,
|
11 |
+
"num_hidden_layers": 48,
|
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 |
+
"moe_intermediate_size": 768,
|
24 |
+
"num_experts_per_tok": 8,
|
25 |
+
"num_experts": 128,
|
26 |
+
"decoder_sparse_step": 1,
|
27 |
+
"norm_topk_prob": true
|
28 |
+
},
|
29 |
+
"vocab_size": 151936,
|
30 |
+
"context_window_size": 40960,
|
31 |
+
"sliding_window_size": -1,
|
32 |
+
"prefill_chunk_size": 2048,
|
33 |
+
"attention_sink_size": -1,
|
34 |
+
"tensor_parallel_shards": 1,
|
35 |
+
"pipeline_parallel_stages": 1,
|
36 |
+
"temperature": 0.6,
|
37 |
+
"presence_penalty": 0.0,
|
38 |
+
"frequency_penalty": 0.0,
|
39 |
+
"repetition_penalty": 1.0,
|
40 |
+
"top_p": 0.95,
|
41 |
+
"tokenizer_files": [
|
42 |
+
"tokenizer.json",
|
43 |
+
"vocab.json",
|
44 |
+
"merges.txt",
|
45 |
+
"tokenizer_config.json"
|
46 |
+
],
|
47 |
+
"tokenizer_info": {
|
48 |
+
"token_postproc_method": "byte_level",
|
49 |
+
"prepend_space_in_encode": false,
|
50 |
+
"strip_space_in_decode": false
|
51 |
+
},
|
52 |
+
"conv_template": {
|
53 |
+
"name": "qwen2",
|
54 |
+
"system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
|
55 |
+
"system_message": "You are a helpful assistant.",
|
56 |
+
"system_prefix_token_ids": null,
|
57 |
+
"add_role_after_system_message": true,
|
58 |
+
"roles": {
|
59 |
+
"user": "<|im_start|>user",
|
60 |
+
"assistant": "<|im_start|>assistant"
|
61 |
+
},
|
62 |
+
"role_templates": {
|
63 |
+
"user": "{user_message}",
|
64 |
+
"assistant": "{assistant_message}",
|
65 |
+
"tool": "{tool_message}"
|
66 |
+
},
|
67 |
+
"messages": [],
|
68 |
+
"seps": [
|
69 |
+
"<|im_end|>\n"
|
70 |
+
],
|
71 |
+
"role_content_sep": "\n",
|
72 |
+
"role_empty_sep": "\n",
|
73 |
+
"stop_str": [
|
74 |
+
"<|endoftext|>",
|
75 |
+
"<|im_end|>"
|
76 |
+
],
|
77 |
+
"stop_token_ids": [
|
78 |
+
151643,
|
79 |
+
151645
|
80 |
+
],
|
81 |
+
"function_string": "",
|
82 |
+
"use_function_calling": false
|
83 |
+
},
|
84 |
+
"pad_token_id": 151643,
|
85 |
+
"bos_token_id": 151643,
|
86 |
+
"eos_token_id": [
|
87 |
+
151645,
|
88 |
+
151643
|
89 |
+
]
|
90 |
+
}
|
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 sha256:3499fe6dd7ed03314c9c24c46871c6755347673244960b9b7d3ad68eebf06831
|
3 |
+
size 622329856
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0db4fb30aee71d818c07af639cc4a524865ff6dc1dfea22b1c73bcd657485de7
|
3 |
+
size 402653184
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afe57a9ae1f82e59430a56a7a8c233b8f4b0aef089a8ddf22cde902ad695315b
|
3 |
+
size 16777216
|
params_shard_100.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da2d3c9aea4dc7e651f186c2b2315a8019513a38a5920d40478d185de806cf71
|
3 |
+
size 16777216
|
params_shard_101.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f386e5e571c2c573be197799dfe6bbbf291c99b08e6990fc8c4fd5dd449d84b8
|
3 |
+
size 402653184
|
params_shard_102.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06b5042a763f4d032f146339d8400470adfa7cebee2dd6048e06498c35325eb9
|
3 |
+
size 805306368
|
params_shard_103.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3945c5ea44a18a546b1a2b6c47e490af9827cc77f51a5ec5a9aa41488ca8582f
|
3 |
+
size 20971520
|
params_shard_104.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:841afd099d28c4662e0c8f62fce9f1188ad5e4eca1d1b6f36b3f7f36324dd3ba
|
3 |
+
size 16777216
|
params_shard_105.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51f3613b30821d85f297d596f11aff30d539b59bc200d0b9a9e74c5b15969dbc
|
3 |
+
size 402653184
|
params_shard_106.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e96964f93759bfd4209d39d4d5e316c1175a109e79844df7ff259bf9f1169305
|
3 |
+
size 805306368
|
params_shard_107.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d57b31f156609653e2a3f6f06d77ae1e7b32de2064a861c8e1587df6e5b76c2
|
3 |
+
size 20971520
|
params_shard_108.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a14b6d318a99df710101eec2dd988ad8fb8795a5b8203aadb07a1725ce274ac5
|
3 |
+
size 16777216
|
params_shard_109.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cc800553ccc452409f998a1b653a6e20b1873798eb089d6e72a70e2ef712408
|
3 |
+
size 402653184
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25f23420baf5b25625a2f8d8a05740d56e120217201b366bf299c12f5f8b9dfd
|
3 |
+
size 402653184
|
params_shard_110.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22718c3ea717f338900bc2a0e2b7ea89526f59c9fa1507c4bc7cd910cd91d4a2
|
3 |
+
size 805306368
|
params_shard_111.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4ef7b63b27c0794251dae3c0216b448802914444616503650ea063091a8ef06
|
3 |
+
size 20971520
|
params_shard_112.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8359521664562ed2e06b0f6540086b5962c6e95db7e1aa6d7644aef3424adca
|
3 |
+
size 16777216
|
params_shard_113.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4afd73b31eae81315aff586e5580e65f4be9e3bc880799504cd280ef95e7635c
|
3 |
+
size 402653184
|
params_shard_114.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7caa7f5f356470367d3c99aa75f1d9edb2f7ed4a60b8d0a9a45fad2c9e2e8011
|
3 |
+
size 805306368
|
params_shard_115.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee41509e310ce6fc7b8a4e11d77862ccc09ffddd0c9c44f6e764e8e26de19496
|
3 |
+
size 20971520
|
params_shard_116.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cf37762492c82fae9d0dc897bd2703a7f3fc13ae1587f383f90eee2658cea5a
|
3 |
+
size 16777216
|
params_shard_117.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd4208cd98697a228e27f54ded282af3650bf99ba88fef39f4c42a858c163d9d
|
3 |
+
size 402653184
|
params_shard_118.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:510dbba3d71026ebf12e5d97d1b289d8c285a16b703d39470b6a0d4a4909699d
|
3 |
+
size 805306368
|
params_shard_119.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e44e096926c64088c83b9391b543d586b43ac8ba0d9ee405ae65a7f2b8ec7ff
|
3 |
+
size 20971520
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5b6d9253f22e08d525c41767716385c5019758a5838b41e66541c22424d93eb
|
3 |
+
size 805306368
|
params_shard_120.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22959bfeb71bb62337781cc93ddbe1645583fb500f88e1dc4007b14d78135451
|
3 |
+
size 16777216
|
params_shard_121.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ca64f4535c677dfe73c1217e38abd46a72ecddf4449f725b24288ec323da267
|
3 |
+
size 402653184
|
params_shard_122.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60d64695fa196f9609bcccb18ad7f6641dfc968b476e5c75a9fc4cd28e5d5cff
|
3 |
+
size 805306368
|
params_shard_123.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d066d5b2d51b3300cc298a925900d12e539126e54c6f30f8ec34b0cec42b2e70
|
3 |
+
size 20971520
|
params_shard_124.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71fd3f14b011cfcd2fa16cb1c3dbc088e414beecd12551fb505227b971241988
|
3 |
+
size 16777216
|
params_shard_125.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6ac9ebc36071330878b7930361f57766cd3b62daeb40291b9ab8217170ec7ed
|
3 |
+
size 402653184
|
params_shard_126.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29c10cc20a3eea848f4415dac89833edc7f51b5b5d7821737f8f67c0ef69a394
|
3 |
+
size 805306368
|
params_shard_127.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96cc663093d34e132d47aed89c03216ff4a54c1aef33f39b3a0d998f7442003c
|
3 |
+
size 20971520
|
params_shard_128.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e99576841d47bd70acbbaeef9ca701452347df2f368ac0e11ebbe159c4861c9
|
3 |
+
size 16777216
|
params_shard_129.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f02644651e02d462261cdd138ccc48b2f92e82eed1a0849a70c3bb0b9d247493
|
3 |
+
size 402653184
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c14d078367f26d1d9b2b726691997e7f6f6688dc9e0cbcde2cdf8f801c3c91a
|
3 |
+
size 20971520
|
params_shard_130.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fe55029a18a876fde57cc83dc2e954b452664afb0fffac18f3c02b832eb0d85
|
3 |
+
size 805306368
|
params_shard_131.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5368655e916dca6f604a8d71b7ce65b6dc62221378dc4e1588e3fac8c7124b62
|
3 |
+
size 20971520
|
params_shard_132.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3499f2e57e2dfa19baefbc8468674e6f9c8d34aae3950c94462750f5338f5947
|
3 |
+
size 16777216
|
params_shard_133.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6b8301e2746d416658cd4802cbac76f0ff6f9fb6ba00a571daf74775757e481
|
3 |
+
size 402653184
|
params_shard_134.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a3e0616664f13ef27088666f4c5ca8061555f86b830a40edf6be640a7742272
|
3 |
+
size 805306368
|
params_shard_135.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e54331b8f6e4dc09e9082a7afbeb7b415b2b2f0a41e44505fa9646b8e3fbcf24
|
3 |
+
size 20971520
|
params_shard_136.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4d40003ea7aadb01030f4e0afe66438a0a98c33060d0df9f070b392ddd500e9
|
3 |
+
size 16777216
|
params_shard_137.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ea3918128fe2d450dd1166fcdc8d676b1da544d33d220f0cc0094f698b11cd8
|
3 |
+
size 402653184
|
params_shard_138.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5074fc7ace2678d98e668f392b529c795809dccfb466b023bab2e2e555e11d2a
|
3 |
+
size 805306368
|
params_shard_139.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14e36b91ef3fb01a2598fbcbe12a10e8c0cfbc286cedff07644a3b01f6e156e0
|
3 |
+
size 20971520
|