Add redpajama-3b instruct model weights
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- mlc-chat-config.json +77 -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_11.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
- params_shard_22.bin +3 -0
- params_shard_23.bin +3 -0
- params_shard_24.bin +3 -0
- params_shard_25.bin +3 -0
- params_shard_26.bin +3 -0
- params_shard_27.bin +3 -0
- params_shard_28.bin +3 -0
- params_shard_29.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_30.bin +3 -0
- params_shard_31.bin +3 -0
- params_shard_32.bin +3 -0
- params_shard_33.bin +3 -0
- params_shard_34.bin +3 -0
- params_shard_35.bin +3 -0
- params_shard_36.bin +3 -0
- params_shard_37.bin +3 -0
- params_shard_38.bin +3 -0
- params_shard_39.bin +3 -0
- params_shard_4.bin +3 -0
- params_shard_40.bin +3 -0
- params_shard_41.bin +3 -0
- params_shard_42.bin +3 -0
- params_shard_43.bin +3 -0
- params_shard_44.bin +3 -0
- params_shard_45.bin +3 -0
- params_shard_46.bin +3 -0
mlc-chat-config.json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "mistral",
|
4 |
+
"quantization": "q4f16_1",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_size": 4096,
|
7 |
+
"intermediate_size": 14336,
|
8 |
+
"num_attention_heads": 32,
|
9 |
+
"num_hidden_layers": 32,
|
10 |
+
"rms_norm_eps": 1e-05,
|
11 |
+
"vocab_size": 32768,
|
12 |
+
"position_embedding_base": 1000000.0,
|
13 |
+
"num_key_value_heads": 8,
|
14 |
+
"head_dim": 128,
|
15 |
+
"context_window_size": 32768,
|
16 |
+
"sliding_window_size": -1,
|
17 |
+
"prefill_chunk_size": 2048,
|
18 |
+
"attention_sink_size": 4,
|
19 |
+
"tensor_parallel_shards": 1,
|
20 |
+
"max_batch_size": 80
|
21 |
+
},
|
22 |
+
"vocab_size": 32768,
|
23 |
+
"context_window_size": 32768,
|
24 |
+
"sliding_window_size": -1,
|
25 |
+
"prefill_chunk_size": 2048,
|
26 |
+
"attention_sink_size": 4,
|
27 |
+
"tensor_parallel_shards": 1,
|
28 |
+
"pipeline_parallel_stages": 1,
|
29 |
+
"temperature": 1.0,
|
30 |
+
"presence_penalty": 0.0,
|
31 |
+
"frequency_penalty": 0.0,
|
32 |
+
"repetition_penalty": 1.0,
|
33 |
+
"top_p": 1.0,
|
34 |
+
"tokenizer_files": [
|
35 |
+
"tokenizer.model",
|
36 |
+
"tokenizer.json",
|
37 |
+
"tokenizer_config.json"
|
38 |
+
],
|
39 |
+
"tokenizer_info": {
|
40 |
+
"token_postproc_method": "byte_fallback",
|
41 |
+
"prepend_space_in_encode": false,
|
42 |
+
"strip_space_in_decode": true
|
43 |
+
},
|
44 |
+
"conv_template": {
|
45 |
+
"name": "LM",
|
46 |
+
"system_template": "{system_message}",
|
47 |
+
"system_message": "",
|
48 |
+
"system_prefix_token_ids": [
|
49 |
+
1
|
50 |
+
],
|
51 |
+
"add_role_after_system_message": true,
|
52 |
+
"roles": {
|
53 |
+
"user": "",
|
54 |
+
"assistant": ""
|
55 |
+
},
|
56 |
+
"role_templates": {
|
57 |
+
"user": "{user_message}",
|
58 |
+
"assistant": "{assistant_message}",
|
59 |
+
"tool": "{tool_message}"
|
60 |
+
},
|
61 |
+
"messages": [],
|
62 |
+
"seps": [
|
63 |
+
""
|
64 |
+
],
|
65 |
+
"role_content_sep": "",
|
66 |
+
"role_empty_sep": "",
|
67 |
+
"stop_str": [],
|
68 |
+
"stop_token_ids": [
|
69 |
+
2
|
70 |
+
],
|
71 |
+
"function_string": "",
|
72 |
+
"use_function_calling": false
|
73 |
+
},
|
74 |
+
"pad_token_id": 0,
|
75 |
+
"bos_token_id": 1,
|
76 |
+
"eos_token_id": 2
|
77 |
+
}
|
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:c311e650fc981865599965f0c24f469498b58a28c0ac6bf4bfbdc83eb65a0fb9
|
3 |
+
size 67108864
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dedf96168491388fdcad8b1bb19cdbf88c866ef2e06d410df886ff68e3681904
|
3 |
+
size 29360128
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:016d717f918adc4fe571aff90559385aff6d3d3400a3bc2238e0437b78d2c0d5
|
3 |
+
size 30949376
|
params_shard_100.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af399034af37a85ce9fc6e79deafa6a2bf19c063f7e92e8b37423fc0580c6b94
|
3 |
+
size 27271168
|
params_shard_101.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c247a6b7feab4eb2b738b184222afe2a6d0922578b16517f9c9a88844d482635
|
3 |
+
size 29360128
|
params_shard_102.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94406b6e9785e0a27c74c44952b581f66fb282e04a485f6043fdf39d28c455bd
|
3 |
+
size 30949376
|
params_shard_103.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:580a9071d05779b3dde9e3464f822b3b1eb624c1d69877804ea271b60147fd88
|
3 |
+
size 58720256
|
params_shard_104.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fecd048bbb94ead3fb216b710f80ccd869e56aa2dd0d50e15e52bf43856022e
|
3 |
+
size 25174016
|
params_shard_105.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:879e939cdf0552704d057c75fda4656f81fc8379655dd24ff74feda86ce1d6fd
|
3 |
+
size 33030144
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4ba4d4825235e9ca52f49c9ec984d13bd1c67a4268f0e270419290fd15694d9
|
3 |
+
size 58720256
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d674a530d2ee503e68fd9b7728b5e71c502350761f2661498eff8d70e6a7a51
|
3 |
+
size 25174016
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81608817f39a61b84d392149902a599da985a268abe0a5c2e97ec35bea34e475
|
3 |
+
size 29360128
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3faf83c25e369b8c4ac314060f5d2adbad9b12d012b9eab015e33ffeb188640
|
3 |
+
size 58720256
|
params_shard_15.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ab9d6ae49516d7c9dfd529618d8d1cc8c0bed6304fdaaa1e1098c6ec15c35cf
|
3 |
+
size 33046528
|
params_shard_16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce9e879001c4206459004bd5ff7cbcb18740ade7c7b4c08c4019af6d4b6d784a
|
3 |
+
size 29360128
|
params_shard_17.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fc5879d4a6c5b70ebe2ecc5e4dbf40ef9c87525c53a98b4d6b9152abbe29923
|
3 |
+
size 58720256
|
params_shard_18.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b39d2a253c9d8d30a925d69ac63502601bb23dde144d76ced3a2890925ed7ac
|
3 |
+
size 22036480
|
params_shard_19.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b657f7b24dfe329890b684dd8e68fe95511d817ac75d2f8170c2fb9ec2063f7
|
3 |
+
size 29360128
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e68edb50a31fd653162fdbc734a9f542795d5f02b65b191a723c27a1f3904e7
|
3 |
+
size 58720256
|
params_shard_20.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:657ab6e9aa249c4bd6eeb001d6e24a32c2b3a668221c4e0ce89c3bc2ec5e0b44
|
3 |
+
size 58720256
|
params_shard_21.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb8c484277abdc6d852f5b5c786c33662476b79662dfd6611ad231b00c433d3a
|
3 |
+
size 27271168
|
params_shard_22.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e91bfb2ba565a69b760406f708d03ad4c8c400f1437a46f735c10b8771da737d
|
3 |
+
size 29360128
|
params_shard_23.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd7f70132e1b902eeb24d0cf021bf77a129c9587d4ab284fff44a101096b490e
|
3 |
+
size 30949376
|
params_shard_24.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d94ade3653fc2f032e20fc346d29e0671d9f5da6bc98ea055c4494a93bb91a82
|
3 |
+
size 58720256
|
params_shard_25.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57f8e05b086af257786fbedc8737e154d26378e36b7a729e4f3cc58afdede233
|
3 |
+
size 25174016
|
params_shard_26.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9a857e7a2f0e605b04c9d93134a8401ef0fc0c75e86a46e4c832070479d3704
|
3 |
+
size 29360128
|
params_shard_27.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65d080451810a86a3e575eba37d8478200a7864ef633dc5a4a903791c870dd85
|
3 |
+
size 58720256
|
params_shard_28.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:178375ec1ca0558cc8b713fd621a5a9efc9ace618f60fd9c4ff7b9da5e74f6ef
|
3 |
+
size 33046528
|
params_shard_29.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc4f30b0b55864559edbf035e84e12febd6381b898813bd431aabca95ebc6827
|
3 |
+
size 29360128
|
params_shard_3.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2af8976024b725f87d035c46584ada29ce80bff3d3ba7c108cca62a3f5f4146
|
3 |
+
size 29360128
|
params_shard_30.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:280f30c8c9e3dc2efdec2ed508e1027fd90aa21a4d8b8d3caa846fbad77ada84
|
3 |
+
size 58720256
|
params_shard_31.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c4dfefd7023138a162d8e466087652e6aed7b8e5e968f829a6bb8f09194a714
|
3 |
+
size 22036480
|
params_shard_32.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cac3c428096e82b094c9c545e400949cf09f8a662a0eb80e086212eda0149eb
|
3 |
+
size 67108864
|
params_shard_33.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea4b8d3cc99329b1984c3da436ef55498b4563d534997ca86ba65fb21270e0f3
|
3 |
+
size 29360128
|
params_shard_34.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:231485e2f892e22205891dbc7927cd1e65ae9a13180170049e81cf45ea8208ff
|
3 |
+
size 31997952
|
params_shard_35.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53370756391dec35339842aaac596e1c1395b48d936f376d70c175245f2c0d03
|
3 |
+
size 58720256
|
params_shard_36.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1d20ee4c29274e5f23c7488be20c2d42e91179d2480b7db34ab754cfea18a1e
|
3 |
+
size 25174016
|
params_shard_37.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2f04966f5df1fbdc6e238c062502b063c54f907cecfd865826bcfa219690148
|
3 |
+
size 29360128
|
params_shard_38.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d673e38a21e628eb43d8f615854513c872476eba8077a84243cc9b522f3aafe1
|
3 |
+
size 58720256
|
params_shard_39.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e96ef688722f5d3a58711a1322c2cdbef182d17c60b82e37df4c917d1d8cf91
|
3 |
+
size 33046528
|
params_shard_4.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7444570f3b9867c0b9d000d106e27d4c2401582d6a021d5ac3ada71c9add8bbe
|
3 |
+
size 58720256
|
params_shard_40.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5eb8c882d35bba684b88240f1c82f08b92b90d4ee90da5df77e44e3e8e584301
|
3 |
+
size 58720256
|
params_shard_41.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d79f0b3332180908d41ae8017eeb6440796f0b813661998499a70581d50dd11e
|
3 |
+
size 32505856
|
params_shard_42.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f73b2103ebeb3a429492007bdd203c32a56427bd5eedebeb59871831d2a259fe
|
3 |
+
size 29360128
|
params_shard_43.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28b19af6046b7858bf8d820dda8da29a7e15b52a948d0b398af81e82756529f2
|
3 |
+
size 58720256
|
params_shard_44.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:610ee03fbce6f8fb7696d9e6d1b2ee6c9e62490c8bc9413495249581560ed5ef
|
3 |
+
size 33046528
|
params_shard_45.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:014a4fd46d45ce120a7d018f892d4f2ec0bc24b55176668b180e4bf27a50b0ac
|
3 |
+
size 29360128
|
params_shard_46.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:285fe659fe42e67cec5b753dc840e53a430f7682c91c0291cb7785163ddf03c2
|
3 |
+
size 58720256
|