Track pytorch_model.bin using LFS
Browse files- .gitattributes +1 -0
- config.json +1 -1
- config.json1 +55 -0
- pytorch_model.bin +2 -2
- quantize_config.json1 +13 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
@@ -44,7 +44,7 @@
|
|
44 |
"tie_word_embeddings": false,
|
45 |
"tokenizer_class": "QWenTokenizer",
|
46 |
"torch_dtype": "float16",
|
47 |
-
"transformers_version": "4.
|
48 |
"use_cache": true,
|
49 |
"use_cache_kernel": false,
|
50 |
"use_cache_quantization": false,
|
|
|
44 |
"tie_word_embeddings": false,
|
45 |
"tokenizer_class": "QWenTokenizer",
|
46 |
"torch_dtype": "float16",
|
47 |
+
"transformers_version": "4.38.2",
|
48 |
"use_cache": true,
|
49 |
"use_cache_kernel": false,
|
50 |
"use_cache_quantization": false,
|
config.json1
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen-7B",
|
3 |
+
"architectures": [
|
4 |
+
"QWenLMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_dropout_prob": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "Qwen/Qwen-7B--configuration_qwen.QWenConfig",
|
9 |
+
"AutoModelForCausalLM": "Qwen/Qwen-7B--modeling_qwen.QWenLMHeadModel"
|
10 |
+
},
|
11 |
+
"bf16": true,
|
12 |
+
"emb_dropout_prob": 0.0,
|
13 |
+
"fp16": false,
|
14 |
+
"fp32": false,
|
15 |
+
"hidden_size": 4096,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 22016,
|
18 |
+
"kv_channels": 128,
|
19 |
+
"layer_norm_epsilon": 1e-06,
|
20 |
+
"max_position_embeddings": 32768,
|
21 |
+
"model_type": "qwen",
|
22 |
+
"no_bias": true,
|
23 |
+
"num_attention_heads": 32,
|
24 |
+
"num_hidden_layers": 32,
|
25 |
+
"onnx_safe": null,
|
26 |
+
"quantization_config": {
|
27 |
+
"bits": 4,
|
28 |
+
"damp_percent": 0.01,
|
29 |
+
"desc_act": false,
|
30 |
+
"group_size": 128,
|
31 |
+
"is_marlin_format": false,
|
32 |
+
"model_file_base_name": null,
|
33 |
+
"model_name_or_path": null,
|
34 |
+
"quant_method": "gptq",
|
35 |
+
"static_groups": false,
|
36 |
+
"sym": true,
|
37 |
+
"true_sequential": true
|
38 |
+
},
|
39 |
+
"rotary_emb_base": 10000,
|
40 |
+
"rotary_pct": 1.0,
|
41 |
+
"scale_attn_weights": true,
|
42 |
+
"seq_length": 8192,
|
43 |
+
"softmax_in_fp32": false,
|
44 |
+
"tie_word_embeddings": false,
|
45 |
+
"tokenizer_class": "QWenTokenizer",
|
46 |
+
"torch_dtype": "float16",
|
47 |
+
"transformers_version": "4.37.2",
|
48 |
+
"use_cache": true,
|
49 |
+
"use_cache_kernel": false,
|
50 |
+
"use_cache_quantization": false,
|
51 |
+
"use_dynamic_ntk": true,
|
52 |
+
"use_flash_attn": true,
|
53 |
+
"use_logn_attn": true,
|
54 |
+
"vocab_size": 151936
|
55 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8534cd59f7e558be8b79beccebf32e156ef81c4a200e873507358e58bfd808ca
|
3 |
+
size 5860862723
|
quantize_config.json1
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"group_size": 128,
|
4 |
+
"damp_percent": 0.01,
|
5 |
+
"desc_act": false,
|
6 |
+
"static_groups": false,
|
7 |
+
"sym": true,
|
8 |
+
"true_sequential": true,
|
9 |
+
"model_name_or_path": null,
|
10 |
+
"model_file_base_name": null,
|
11 |
+
"is_marlin_format": false,
|
12 |
+
"quant_method": "gptq"
|
13 |
+
}
|