Hugging Face's logo

pytorch
/
Qwen3-8B-AWQ-INT4

Text Generation
Transformers
PyTorch
English
qwen3
torchao
conversational
text-generation-inference
Model card Files
xet
Community
jerryzh168 commited on
Commit
8fdd7c1
·
verified ·
1 Parent(s): d3cbc97

Upload Qwen3ForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +39 -30
  2. generation_config.json +1 -1
  3. pytorch_model-00001-of-00002.bin +1 -1
  4. pytorch_model-00002-of-00002.bin +2 -2
  5. pytorch_model.bin.index.json +1 -1
config.json CHANGED
@@ -62,39 +62,48 @@
62
  "quant_type": {
63
  "default": {
64
  "_data": {
65
- "base_config": {
66
- "_data": {
67
- "group_size": 128,
68
- "int4_choose_qparams_algorithm": {
69
- "_data": "TINYGEMM",
70
- "_type": "Int4ChooseQParamsAlgorithm"
71
- },
72
- "int4_packing_format": {
73
- "_data": "PLAIN",
74
- "_type": "Int4PackingFormat"
75
- },
76
- "layout": {
77
- "_data": {
78
- "inner_k_tiles": 8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
  },
80
- "_type": "TensorCoreTiledLayout",
81
- "_version": 1
82
  },
83
- "preserve_zero": null,
84
- "set_inductor_config": true,
85
- "use_hqq": false,
86
- "zero_point_domain": {
87
- "_data": "NONE",
88
- "_type": "ZeroPointDomain"
89
- }
90
  },
91
- "_type": "Int4WeightOnlyConfig",
92
- "_version": 2
93
- },
94
- "scale_search_space_size": 20,
95
- "step": "prepare_for_loading"
96
  },
97
- "_type": "AWQConfig",
98
  "_version": 1
99
  }
100
  },
@@ -107,7 +116,7 @@
107
  "sliding_window": null,
108
  "tie_word_embeddings": false,
109
  "torch_dtype": "bfloat16",
110
- "transformers_version": "4.55.4",
111
  "use_cache": true,
112
  "use_sliding_window": false,
113
  "vocab_size": 151936
 
62
  "quant_type": {
63
  "default": {
64
  "_data": {
65
+ "module_fqn_to_config": {
66
+ "_default": {
67
+ "_data": {
68
+ "base_config": {
69
+ "_data": {
70
+ "group_size": 128,
71
+ "int4_choose_qparams_algorithm": {
72
+ "_data": "TINYGEMM",
73
+ "_type": "Int4ChooseQParamsAlgorithm"
74
+ },
75
+ "int4_packing_format": {
76
+ "_data": "PLAIN",
77
+ "_type": "Int4PackingFormat"
78
+ },
79
+ "layout": {
80
+ "_data": {
81
+ "inner_k_tiles": 8
82
+ },
83
+ "_type": "TensorCoreTiledLayout",
84
+ "_version": 1
85
+ },
86
+ "preserve_zero": null,
87
+ "set_inductor_config": true,
88
+ "use_hqq": false,
89
+ "zero_point_domain": {
90
+ "_data": "NONE",
91
+ "_type": "ZeroPointDomain"
92
+ }
93
+ },
94
+ "_type": "Int4WeightOnlyConfig",
95
+ "_version": 2
96
  },
97
+ "scale_search_space_size": 20,
98
+ "step": "prepare_for_loading"
99
  },
100
+ "_type": "AWQConfig",
101
+ "_version": 1
 
 
 
 
 
102
  },
103
+ "lm_head": null
104
+ }
 
 
 
105
  },
106
+ "_type": "ModuleFqnToConfig",
107
  "_version": 1
108
  }
109
  },
 
116
  "sliding_window": null,
117
  "tie_word_embeddings": false,
118
  "torch_dtype": "bfloat16",
119
+ "transformers_version": "4.55.2",
120
  "use_cache": true,
121
  "use_sliding_window": false,
122
  "vocab_size": 151936
generation_config.json CHANGED
@@ -9,5 +9,5 @@
9
  "temperature": 0.6,
10
  "top_k": 20,
11
  "top_p": 0.95,
12
- "transformers_version": "4.55.4"
13
  }
 
9
  "temperature": 0.6,
10
  "top_k": 20,
11
  "top_p": 0.95,
12
+ "transformers_version": "4.55.2"
13
  }
pytorch_model-00001-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20da9306eb208967f598cf115a672b36d68ca5853d8ee0c2fc6904b566d1732e
3
  size 4938272073
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8bfaec3246733cf5bef19a2e6686d539e2a97e235c44d9f0e501ae5e494e2d
3
  size 4938272073
pytorch_model-00002-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:760a161b40a3e47adedecad1feeac1c8b6b24b1f3f1b23a58e5b785b44df736e
3
- size 330623983
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f41a2ea7d01f35ed3c0ecd8cab39da1cd7bc2ad48be7c46dc8fab80b5628bfa9
3
+ size 1244661564
pytorch_model.bin.index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "metadata": {
3
  "total_parameters": 8190735360,
4
- "total_size": 5268490240
5
  },
6
  "weight_map": {
7
  "lm_head.weight": "pytorch_model-00002-of-00002.bin",
 
1
  {
2
  "metadata": {
3
  "total_parameters": 8190735360,
4
+ "total_size": 6182529024
5
  },
6
  "weight_map": {
7
  "lm_head.weight": "pytorch_model-00002-of-00002.bin",