Upload folder using huggingface_hub
Browse files- config.json +40 -0
- model-00001-of-00012.safetensors +3 -0
- model-00002-of-00012.safetensors +3 -0
- model-00003-of-00012.safetensors +3 -0
- model-00004-of-00012.safetensors +3 -0
- model-00005-of-00012.safetensors +3 -0
- model-00006-of-00012.safetensors +3 -0
- model-00007-of-00012.safetensors +3 -0
- model-00008-of-00012.safetensors +3 -0
- model-00009-of-00012.safetensors +3 -0
- model-00010-of-00012.safetensors +3 -0
- model-00011-of-00012.safetensors +3 -0
- model-00012-of-00012.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantize_config.json +13 -0
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./save_folder",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 12288,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 32768,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 96,
|
17 |
+
"num_hidden_layers": 88,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"quantization_config": {
|
20 |
+
"bits": 4,
|
21 |
+
"checkpoint_format": "gptq",
|
22 |
+
"damp_percent": 0.1,
|
23 |
+
"desc_act": true,
|
24 |
+
"group_size": 1024,
|
25 |
+
"model_file_base_name": null,
|
26 |
+
"model_name_or_path": null,
|
27 |
+
"quant_method": "gptq",
|
28 |
+
"static_groups": false,
|
29 |
+
"sym": true,
|
30 |
+
"true_sequential": true
|
31 |
+
},
|
32 |
+
"rms_norm_eps": 1e-05,
|
33 |
+
"rope_theta": 1000000.0,
|
34 |
+
"sliding_window": null,
|
35 |
+
"tie_word_embeddings": false,
|
36 |
+
"torch_dtype": "float16",
|
37 |
+
"transformers_version": "4.43.1",
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 32768
|
40 |
+
}
|
model-00001-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3386ba7120e1335eec9da18620942a362569eb575a60cd870e34e8b5618a823d
|
3 |
+
size 5267330480
|
model-00002-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff209c64b5803158abb2f305df30e38e9048ceb41307a1a1ee3c9aa1d99b6772
|
3 |
+
size 5307763904
|
model-00003-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c01df5b88c0a9299e94be6ff5338210ef8a2174674b3317ba25d14b9de760a75
|
3 |
+
size 5307829416
|
model-00004-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f0d83c2516a712c3337105b84ef6acedf6059083f40b8339792b87385211bff
|
3 |
+
size 5213071088
|
model-00005-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a6fabf130b6b60bdc64f24922495b8e727de5bb773a4945cdafe2e9c87141bb
|
3 |
+
size 5225451688
|
model-00006-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67d4107b097864f45792c6f346905de7165297382bdf4ba70c8da0512075d434
|
3 |
+
size 5213071120
|
model-00007-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d2243329e186eec6d7e56d6113e9398e76227b6e550e39a8ad2307c2474887e
|
3 |
+
size 5225451688
|
model-00008-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ee9401a9c862ddca2b8b8a06d07136891d573a4633e5f7ae906b529f221a631
|
3 |
+
size 5213071088
|
model-00009-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcd84d88620f58afc3b0056d5538efbfb4ee706c58b532c2b18baaa59ca68b15
|
3 |
+
size 5225451720
|
model-00010-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf81158685295519353d6d46945152562043db6ea60c2e670b50b8be6e691abb
|
3 |
+
size 5213071088
|
model-00011-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7df61df771242a568147384d30c23072048aac72cbb2e01644cfaf824a486bc3
|
3 |
+
size 5225451688
|
model-00012-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e625f0054cd59892b1ab400673ef900f1cd5e9261992d70a538552000d98260f
|
3 |
+
size 5212956272
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
quantize_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 1024,
|
4 |
+
"damp_percent": 0.1,
|
5 |
+
"desc_act": true,
|
6 |
+
"static_groups": false,
|
7 |
+
"sym": true,
|
8 |
+
"true_sequential": true,
|
9 |
+
"model_name_or_path": null,
|
10 |
+
"model_file_base_name": null,
|
11 |
+
"quant_method": "gptq",
|
12 |
+
"checkpoint_format": "gptq"
|
13 |
+
}
|