GPTQ model commit
Browse files- config.json +57 -0
- model.safetensors +3 -0
- quantize_config.json +11 -0
config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/workspace/process/mlabonne_neuralbeagle14-7b/source",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"sliding_window": 4096,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.37.0.dev0",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32000,
|
28 |
+
"quantization_config": {
|
29 |
+
"bits": 4,
|
30 |
+
"group_size": 128,
|
31 |
+
"damp_percent": 0.1,
|
32 |
+
"desc_act": true,
|
33 |
+
"static_groups": false,
|
34 |
+
"sym": true,
|
35 |
+
"true_sequential": true,
|
36 |
+
"model_name_or_path": null,
|
37 |
+
"model_file_base_name": "model",
|
38 |
+
"quant_method": "gptq",
|
39 |
+
"modules_in_block_to_quantize": [
|
40 |
+
[
|
41 |
+
"self_attn.k_proj",
|
42 |
+
"self_attn.v_proj",
|
43 |
+
"self_attn.q_proj"
|
44 |
+
],
|
45 |
+
[
|
46 |
+
"self_attn.o_proj"
|
47 |
+
],
|
48 |
+
[
|
49 |
+
"mlp.up_proj",
|
50 |
+
"mlp.gate_proj"
|
51 |
+
],
|
52 |
+
[
|
53 |
+
"mlp.down_proj"
|
54 |
+
]
|
55 |
+
]
|
56 |
+
}
|
57 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e99d98f7dbbf3e2bc30ff195bd1b81ff34d8d1a5652d626c8677fbe6941d9a29
|
3 |
+
size 4158662216
|
quantize_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
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": "model"
|
11 |
+
}
|