Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- mlc-chat-config.json +87 -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
- params_shard_14.bin +3 -0
- params_shard_140.bin +3 -0
mlc-chat-config.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "llama",
|
4 |
+
"quantization": "q4f16_1",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_size": 8192,
|
7 |
+
"intermediate_size": 28672,
|
8 |
+
"num_attention_heads": 64,
|
9 |
+
"num_hidden_layers": 80,
|
10 |
+
"rms_norm_eps": 1e-05,
|
11 |
+
"vocab_size": 128256,
|
12 |
+
"tie_word_embeddings": false,
|
13 |
+
"position_embedding_base": 500000.0,
|
14 |
+
"rope_scaling": {
|
15 |
+
"factor": 8.0,
|
16 |
+
"high_freq_factor": 4.0,
|
17 |
+
"low_freq_factor": 1.0,
|
18 |
+
"original_max_position_embeddings": 8192,
|
19 |
+
"rope_type": "llama3"
|
20 |
+
},
|
21 |
+
"context_window_size": 131072,
|
22 |
+
"prefill_chunk_size": 8192,
|
23 |
+
"num_key_value_heads": 8,
|
24 |
+
"head_dim": 128,
|
25 |
+
"tensor_parallel_shards": 1,
|
26 |
+
"pipeline_parallel_stages": 1,
|
27 |
+
"max_batch_size": 128,
|
28 |
+
"disaggregation": false
|
29 |
+
},
|
30 |
+
"vocab_size": 128256,
|
31 |
+
"context_window_size": 131072,
|
32 |
+
"sliding_window_size": -1,
|
33 |
+
"prefill_chunk_size": 8192,
|
34 |
+
"attention_sink_size": -1,
|
35 |
+
"tensor_parallel_shards": 1,
|
36 |
+
"pipeline_parallel_stages": 1,
|
37 |
+
"temperature": 1.0,
|
38 |
+
"presence_penalty": 0.0,
|
39 |
+
"frequency_penalty": 0.0,
|
40 |
+
"repetition_penalty": 1.0,
|
41 |
+
"top_p": 1.0,
|
42 |
+
"tokenizer_files": [
|
43 |
+
"tokenizer.json",
|
44 |
+
"tokenizer_config.json"
|
45 |
+
],
|
46 |
+
"tokenizer_info": {
|
47 |
+
"token_postproc_method": "byte_level",
|
48 |
+
"prepend_space_in_encode": false,
|
49 |
+
"strip_space_in_decode": false
|
50 |
+
},
|
51 |
+
"conv_template": {
|
52 |
+
"name": "deepseek_v3",
|
53 |
+
"system_template": "<\uff5cbegin\u2581of\u2581sentence\uff5c>{system_message}",
|
54 |
+
"system_message": "You are a helpful assistant.",
|
55 |
+
"system_prefix_token_ids": null,
|
56 |
+
"add_role_after_system_message": true,
|
57 |
+
"roles": {
|
58 |
+
"user": "<\uff5cUser\uff5c>",
|
59 |
+
"assistant": "<\uff5cAssistant\uff5c>"
|
60 |
+
},
|
61 |
+
"role_templates": {
|
62 |
+
"user": "{user_message}",
|
63 |
+
"assistant": "{assistant_message}",
|
64 |
+
"tool": "{tool_message}"
|
65 |
+
},
|
66 |
+
"messages": [],
|
67 |
+
"seps": [
|
68 |
+
"",
|
69 |
+
"<\uff5cend\u2581of\u2581sentence\uff5c>"
|
70 |
+
],
|
71 |
+
"role_content_sep": "",
|
72 |
+
"role_empty_sep": "",
|
73 |
+
"stop_str": [],
|
74 |
+
"stop_token_ids": [
|
75 |
+
151643
|
76 |
+
],
|
77 |
+
"function_string": "",
|
78 |
+
"use_function_calling": false
|
79 |
+
},
|
80 |
+
"pad_token_id": 0,
|
81 |
+
"bos_token_id": 128000,
|
82 |
+
"eos_token_id": [
|
83 |
+
128001,
|
84 |
+
128008,
|
85 |
+
128009
|
86 |
+
]
|
87 |
+
}
|
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 sha256:1f24c9fbbc6920629c876855111b3766a293cc06671d8145f1494147be5a61b7
|
3 |
+
size 525336576
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9c8c24bf301c2d62a32504830c5349c1e3d97ac56e3986a8b8a3a2087be0ec2
|
3 |
+
size 65667072
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f37f62d1681a0360569fb0356563d5ae7c18d32fe04945f1471eb16045f61e0
|
3 |
+
size 234881024
|
params_shard_100.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8930ef36f34b354449faecfae6cf58da29644ccaf1cf7569c1126675e65f7e63
|
3 |
+
size 29360128
|
params_shard_101.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86b716c9985ff4b88ca7bd03ea871e4f63bfc36e95c66138f02c5298073b0bc9
|
3 |
+
size 117440512
|
params_shard_102.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d3d58693fb30ead9dc1cbaa166abf944c38cd55bf54b9d9b94a356351421458
|
3 |
+
size 24150016
|
params_shard_103.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e1bea1a555358ec5fb81abe629dda7cae790b0be71a3b982339cd5fd0e9aff5
|
3 |
+
size 41943040
|
params_shard_104.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b172436280ae8389ca8c9ebb9bd2daae07d2fabf4b320dc886efbc23d7908fc
|
3 |
+
size 33554432
|
params_shard_105.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7bfa18718992f33b90bc777c8feaf616f9d6ffde01b9f4392fd8c4a47cf0d9f
|
3 |
+
size 234881024
|
params_shard_106.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a6bc0f4938131106297dd0014883bfac09fbe7c85364f7510bbf2f23a7ad97b
|
3 |
+
size 29360128
|
params_shard_107.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5111a7e11043155deecd995410b33d7a66a437f2f93a98b203cebc26e098d00
|
3 |
+
size 117440512
|
params_shard_108.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77c84ef32d5e8eac0935e5d4b2e58b38855a64a762d2205b445b2cc2c5c2dbc1
|
3 |
+
size 24150016
|
params_shard_109.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d21a468c7f6569317476f9d924300dcb24b85e8409bc2a14b2c6a4e34a0375a
|
3 |
+
size 41943040
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f8bf44967d621638f96b9de3ecccc44acd46e44ed64339478777972e0908cff
|
3 |
+
size 29360128
|
params_shard_110.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d4b63b8669bd9af949400e445b97ec346d245a70caad68e55eeca80e9c3249c
|
3 |
+
size 33554432
|
params_shard_111.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:086f3976daac47f7a5c921c1e8ab663379f9dab07cbdd4a3fc3b8c502b9bad57
|
3 |
+
size 234881024
|
params_shard_112.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25df3d30007e472f000b834eb08c4e586c1f92da7d66b3d27ea334110e11d463
|
3 |
+
size 29360128
|
params_shard_113.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a575b41f389e9f36309eee57d552145b8a7646e353726f4306311d4f12199bbe
|
3 |
+
size 117440512
|
params_shard_114.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6557f1f1ed51bcac1cab52b1f4628d23e5683c5b3bda13152a3ead429a50d332
|
3 |
+
size 24150016
|
params_shard_115.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f241066b7238a36d5303cf8c9fd772d4e28e2e2bb132069eb70127b6b571368
|
3 |
+
size 41943040
|
params_shard_116.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5c590ca2aee560a781875c48bd6b48db4ca6e92a681d1f2f82aef22fd3ce440
|
3 |
+
size 33554432
|
params_shard_117.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbe8ba31d7e2a19be6b2e23147024864216f2602352149b887583e661729146d
|
3 |
+
size 234881024
|
params_shard_118.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b963576b1387bc1c6b5fdb4f70912892ac8a4c0ba03c4510b7d3a20cd03eab51
|
3 |
+
size 29360128
|
params_shard_119.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:543f55987600991106d03bd66fea20e1428a0e4c681cedd27ed954845ecb8f19
|
3 |
+
size 117440512
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66808c7061150f58165ac7dd2dfda33aa5e07dbdc27020329c61d938061dc38e
|
3 |
+
size 117440512
|
params_shard_120.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7edec0c4e3fd748b93404d895106e55870a179d45647b4ea9084c2def049559
|
3 |
+
size 24150016
|
params_shard_121.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfa9bf3e125ac8332e2e041d61fee289cb4484e7ddb2ff03fc77b80a5ed55a4c
|
3 |
+
size 41943040
|
params_shard_122.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9575ab3ca1dd7e46de8129f3955d168fab0686814d086c23448d45150b78c1c
|
3 |
+
size 33554432
|
params_shard_123.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dec7c452370c7ac81844e1c93d4e0ce0bb727c9d85b99d0c66f4aaac80efc6d
|
3 |
+
size 234881024
|
params_shard_124.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a789adff8d273f87d671ffb839ee14534af5a5600a6d53137c2768ecbcf6238
|
3 |
+
size 29360128
|
params_shard_125.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94ca3545d9f7f1a619ed2582e09d4303e2e459d48f9826d12b701c9c52abb8a7
|
3 |
+
size 117440512
|
params_shard_126.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1799d3c2c53d6951e36082446b44834acbb82f20a5db8583de4ac13cb414e6a5
|
3 |
+
size 24150016
|
params_shard_127.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:103a668018b91208ff4e20f51c7f034ed429158621877958a661c657fa69f007
|
3 |
+
size 41943040
|
params_shard_128.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:364e2ad330c0e9af06ed9c5e2fbf279152b11065fa345361baae09b6f5e06933
|
3 |
+
size 33554432
|
params_shard_129.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07be00ac56dd1a3fb8980c948bd770c5cbd8bec49f219352fa2dd0463c9ff92c
|
3 |
+
size 234881024
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42baad1d9134c150d311cf4003a61b401cfc7a93a55aaf35d96e1313605c0539
|
3 |
+
size 41943040
|
params_shard_130.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2d7dd08205c4bbbadae1d34da1cca55e0ca3644f9fba73fd48119c5e78e09fc
|
3 |
+
size 29360128
|
params_shard_131.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd3ce093595cdf6c5f8f5067429bf124552dc624cf9131af38122c67787a60d9
|
3 |
+
size 117440512
|
params_shard_132.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b9fe5dcbce1ffee2f746042c4b7e05d4a8200240fa702a2e88ed766856fbd94
|
3 |
+
size 24150016
|
params_shard_133.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ee5c86049ae401baf1e0f63e566de3a4fefe890ae71d109f8af2b11a45ab5d0
|
3 |
+
size 41943040
|
params_shard_134.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d045f90737fe2aa114ca0e5226ea1038a0464693478ced0e382ece85ef42e32c
|
3 |
+
size 33554432
|
params_shard_135.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:432646db728dc8cc411a12cc223e70f497810c569c3e9889c82ba1be2e12817b
|
3 |
+
size 234881024
|
params_shard_136.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73ac714308cfd9b24499ac1b12d9f1e5779881397ffc8c8525810eb31015a9d5
|
3 |
+
size 29360128
|
params_shard_137.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90e47b91094f9342e6716378794c232c19bb6a6cd1fed0e777760bc675dc201a
|
3 |
+
size 117440512
|
params_shard_138.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38217d06ff42696fac96006b061a676ac1231900fbf64a32751ae83c92b020af
|
3 |
+
size 24150016
|
params_shard_139.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a41511014e9e25e810edcf6bde878f07cad3818120236454854abaf4205800c
|
3 |
+
size 41943040
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c67885fe3300a3b81cc614189327203e11bea3eea97055f10ccfa1e56953d47c
|
3 |
+
size 33554432
|
params_shard_140.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8a2f8ecbf2dbd8edb758939e021917a5f9817cda556034f5d85f5c57c8e654a
|
3 |
+
size 33554432
|