Charlie Ruan
commited on
Commit
•
e75f3ac
1
Parent(s):
ece2aed
Add converted weights
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- logs.txt +0 -0
- 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
logs.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mlc-chat-config.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "llama",
|
4 |
+
"quantization": "q0f16",
|
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 |
+
"low_freq_factor": 1.0,
|
17 |
+
"high_freq_factor": 4.0,
|
18 |
+
"original_max_position_embeddings": 8192,
|
19 |
+
"rope_type": "llama3"
|
20 |
+
},
|
21 |
+
"context_window_size": 131072,
|
22 |
+
"prefill_chunk_size": 2048,
|
23 |
+
"num_key_value_heads": 8,
|
24 |
+
"head_dim": 128,
|
25 |
+
"tensor_parallel_shards": 1,
|
26 |
+
"max_batch_size": 80
|
27 |
+
},
|
28 |
+
"vocab_size": 128256,
|
29 |
+
"context_window_size": 131072,
|
30 |
+
"sliding_window_size": -1,
|
31 |
+
"prefill_chunk_size": 2048,
|
32 |
+
"attention_sink_size": -1,
|
33 |
+
"tensor_parallel_shards": 1,
|
34 |
+
"temperature": 0.6,
|
35 |
+
"presence_penalty": 0.0,
|
36 |
+
"frequency_penalty": 0.0,
|
37 |
+
"repetition_penalty": 1.0,
|
38 |
+
"top_p": 0.9,
|
39 |
+
"tokenizer_files": [
|
40 |
+
"tokenizer.json",
|
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": "llama-3_1",
|
50 |
+
"system_template": "<|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|>",
|
51 |
+
"system_message": "You are a helpful, respectful and honest assistant.",
|
52 |
+
"system_prefix_token_ids": [
|
53 |
+
128000
|
54 |
+
],
|
55 |
+
"add_role_after_system_message": true,
|
56 |
+
"roles": {
|
57 |
+
"user": "<|start_header_id|>user",
|
58 |
+
"assistant": "<|start_header_id|>assistant"
|
59 |
+
},
|
60 |
+
"role_templates": {
|
61 |
+
"user": "{user_message}",
|
62 |
+
"assistant": "{assistant_message}",
|
63 |
+
"tool": "{tool_message}"
|
64 |
+
},
|
65 |
+
"messages": [],
|
66 |
+
"seps": [
|
67 |
+
"<|eot_id|>"
|
68 |
+
],
|
69 |
+
"role_content_sep": "<|end_header_id|>\n\n",
|
70 |
+
"role_empty_sep": "<|end_header_id|>\n\n",
|
71 |
+
"stop_str": [],
|
72 |
+
"stop_token_ids": [
|
73 |
+
128001,
|
74 |
+
128008,
|
75 |
+
128009
|
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:dc2dabfaed3a831eeb7b232e8853e3af89b1132e36d24d79c66270c332e62a07
|
3 |
+
size 2101346304
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ffb3f2735de9b562c99f4b71ccee7ce2dda72ee0e403bc5a23de6cb690185d5
|
3 |
+
size 2101346304
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d6259c9d7e5f5d799ad80bae0c154bc32de5dfcba898678dd45c2a2e573a533
|
3 |
+
size 469762048
|
params_shard_100.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af76a331efe1fda8302cc81181fe1b00ca12179314916837da1e7b21d627f4f4
|
3 |
+
size 469762048
|
params_shard_101.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b2a431e7467996a3b1cba689afcead705589ab2fab5b1d0fd796e037e5b194b
|
3 |
+
size 939524096
|
params_shard_102.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1f8c9ae26c4031edd07e36e521de4db3f37f1057d771d2e076031e8f6cedf34
|
3 |
+
size 167772160
|
params_shard_103.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:164ec7d1844e533730ec7f95a23db099082015ac77718432f786e0b1d4e91785
|
3 |
+
size 134217728
|
params_shard_104.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21eebd02aa985b0eb69acae348c374d0969eb57d313ab754b85f3e2bd2a154da
|
3 |
+
size 469762048
|
params_shard_105.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3cc739bdc8a5d84bc3850d786eb794cb88456687eeb9abd09bf99960f70a800
|
3 |
+
size 939524096
|
params_shard_106.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44bde8fe58c9dcaa7455e975a9d0ccad1a8753784da6febc4aefe1c9efbaaab0
|
3 |
+
size 167772160
|
params_shard_107.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c10426b84a4245f8e8b0f53b4630297039c79c2ffaf5d971aebbb83641cc35cf
|
3 |
+
size 134217728
|
params_shard_108.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06c32f3017c6b10b4bf1dc81f628d9795430f1bbb75aef472ed4ae5d3755e835
|
3 |
+
size 167772160
|
params_shard_109.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93a0e9c373d68659f89287d87330fd8c7347020831e637db7eb3a73452311719
|
3 |
+
size 134217728
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f8c0cce51d107ebbc6e1f12dc94043193a93415870c985099fba6394909954d
|
3 |
+
size 939524096
|
params_shard_110.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39c677576bad865ea27ede25e77a72d4f9ed43a0a5ec3340f870643a2330ba4b
|
3 |
+
size 469762048
|
params_shard_111.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b4a42ba8498803c84c2fee9797ad646f73d7a137a28f8cd346ece389c809339
|
3 |
+
size 939524096
|
params_shard_112.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c05d187861288adcfeab1434d7f3d8a885698511b14651367abd404bbb5e19fc
|
3 |
+
size 469762048
|
params_shard_113.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46f85f5724d350921b81e8a7ee939ec7a51b1b345ee9d9d457f92eee8dbb0a96
|
3 |
+
size 939524096
|
params_shard_114.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e7f2466e152f2ace5d968308db5511dbfb9a94541d0f4219b4edf524c733d67
|
3 |
+
size 167772160
|
params_shard_115.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30ecbc019d6bbe563d77825098e91d66846250e349809b0d3412e007de2141a0
|
3 |
+
size 134217728
|
params_shard_116.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b0ca0246f7afcb360c0eec22b3b3512ec71c9fc765503cbb9fbe10ef0095fcc
|
3 |
+
size 469762048
|
params_shard_117.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c603b7c9e35b454c8c7e426ac6c36323d05a941ebb5b24de5fb414e4b5a05d28
|
3 |
+
size 939524096
|
params_shard_118.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c91dde31f3c5b7f99cfbaea6c1d97389b511973bccae7cb8eb014c0adf7e6799
|
3 |
+
size 167772160
|
params_shard_119.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2925d940f9ecfaa68913a01ab7f41511d56c722eaaa24fa37234e947eee67fa3
|
3 |
+
size 134217728
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5db588ce3336853596fdc84c31ed3a7c5d6c2ce8644334a67909ade1ba2d6f5e
|
3 |
+
size 167772160
|
params_shard_120.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f21ae1b2811315ab67524cedaddd9dd93b4717f00e4ef1139ecc7cc10c0b7f7
|
3 |
+
size 167772160
|
params_shard_121.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da92bca6bb9b1a9e15b5174da2665051637922f7d29b3edb66b4cd71f61132e7
|
3 |
+
size 469762048
|
params_shard_122.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e78eaefde0bb867ca3ed26d8798c29f761e92bc04795975758a312505215dbc
|
3 |
+
size 939524096
|
params_shard_123.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42348edd3debd11309bf668d3d9f48801aa21d2c1632231b66c4ee284ddb55e2
|
3 |
+
size 134217728
|
params_shard_124.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:532c92396c0aa1bb9a40abb7cd93ca53afc2370beedbda283ce8a0b18869e8e1
|
3 |
+
size 469762048
|
params_shard_125.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4b8b99d0b80c419c9e2733cd810fd5d01d4282a8203c7f22191a53eaae3be89
|
3 |
+
size 939524096
|
params_shard_126.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92376ce55c7ecd4b73a881e7d35a3eed6dd1373c5d791988b387682864e87f7e
|
3 |
+
size 167772160
|
params_shard_127.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8caf170073ad594de15a11f90f36c0a1571f6106966e86061912b06d8e029d19
|
3 |
+
size 134217728
|
params_shard_128.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c501f38703cdc06abb1e30de6ed4f41f23640a1065bfb00a3240f97772b79ad
|
3 |
+
size 469762048
|
params_shard_129.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f9029a6a2edb9a1430fed2876651b727a65ad957cc11d2fc766ff077ec19d70
|
3 |
+
size 939524096
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bba5e18cd21c997c3ecdd0ca17a764a66c65d9073818b42f801f55c025829094
|
3 |
+
size 134217728
|
params_shard_130.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae38969bad84ed27610ce5b9a34b6a70c9451c445ee4667028e8cb10a39077c2
|
3 |
+
size 167772160
|
params_shard_131.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de0a8e169d7d1cd5ca03f20b2a9f65ec655ae2674d7a5a2739957d05934b815d
|
3 |
+
size 134217728
|
params_shard_132.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0beb24e9fab9f1423b4a9ab48d3b1fc451e9aa0ce2ebcbd1e92bbd8d78e8dacc
|
3 |
+
size 469762048
|
params_shard_133.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5bfa30d79fea49910172791a60f7371159c1f31a059391b844c333809d88619
|
3 |
+
size 939524096
|
params_shard_134.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8632929a854f9a3b19fa892cb476cb0aff1a4708fbad328f195c64c1abb87443
|
3 |
+
size 167772160
|
params_shard_135.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d06155694fd1344c1b0b46bc87fe0b1938b5bb7aac34b27fb55d54c5881e931
|
3 |
+
size 134217728
|
params_shard_136.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94da7d86b4983e8cbe9d95856904e53aae0eb52a1807587e671629a744daf562
|
3 |
+
size 469762048
|
params_shard_137.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bd4162d4af282be3a4c6d6d8a960c0f93f7b16761313719fbc90bb551c3870c
|
3 |
+
size 939524096
|
params_shard_138.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e62dfd5547d2369e1d3688ceae896518181cf78c2c052b4b05f3abb99c97b77
|
3 |
+
size 167772160
|
params_shard_139.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb5edcf37225df41a517a3994e3ed0ce8b729d26cb6c9ec72cdbe7966d101183
|
3 |
+
size 134217728
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:531f65b6d2c685fadb3ed48493ed4c36fd72643083ac0fa48cc2af41b1a27cd1
|
3 |
+
size 469762048
|