Hugging Face's logo

Satwik11
/
QwQ-32B-Preview-quantized-autoround-GPTQ-sym-4bit

Safetensors
English
qwen2
4-bit precision
gptq
Model card Files Community
1
Satwik11 commited on
Commit
c375d49
•
1 Parent(s): f19e1e1

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. config.json +121 -0
  4. generation_config.json +13 -0
  5. merges.txt +0 -0
  6. model-00001-of-00004.safetensors +3 -0
  7. model-00002-of-00004.safetensors +3 -0
  8. model-00003-of-00004.safetensors +3 -0
  9. model-00004-of-00004.safetensors +3 -0
  10. model.safetensors.index.json +0 -0
  11. quantize_config.json +92 -0
  12. special_tokens_map.json +31 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +207 -0
  15. vocab.json +0 -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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/QwQ-32B-Preview",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 64,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 64,
18
+ "num_key_value_heads": 8,
19
+ "quantization_config": {
20
+ "amp": true,
21
+ "autoround_version": "0.4.1",
22
+ "batch_size": 1,
23
+ "bits": 4,
24
+ "damp_percent": 0.01,
25
+ "data_type": "int",
26
+ "desc_act": false,
27
+ "enable_minmax_tuning": true,
28
+ "enable_norm_bias_tuning": false,
29
+ "enable_quanted_input": true,
30
+ "gradient_accumulate_steps": 1,
31
+ "group_size": 128,
32
+ "iters": 512,
33
+ "low_gpu_mem_usage": true,
34
+ "lr": 0.001953125,
35
+ "minmax_lr": 0.001953125,
36
+ "nsamples": 128,
37
+ "quant_method": "gptq",
38
+ "scale_dtype": "torch.float16",
39
+ "seqlen": 2048,
40
+ "sym": true,
41
+ "to_quant_block_names": [
42
+ [
43
+ "model.layers.0",
44
+ "model.layers.1",
45
+ "model.layers.2",
46
+ "model.layers.3",
47
+ "model.layers.4",
48
+ "model.layers.5",
49
+ "model.layers.6",
50
+ "model.layers.7",
51
+ "model.layers.8",
52
+ "model.layers.9",
53
+ "model.layers.10",
54
+ "model.layers.11",
55
+ "model.layers.12",
56
+ "model.layers.13",
57
+ "model.layers.14",
58
+ "model.layers.15",
59
+ "model.layers.16",
60
+ "model.layers.17",
61
+ "model.layers.18",
62
+ "model.layers.19",
63
+ "model.layers.20",
64
+ "model.layers.21",
65
+ "model.layers.22",
66
+ "model.layers.23",
67
+ "model.layers.24",
68
+ "model.layers.25",
69
+ "model.layers.26",
70
+ "model.layers.27",
71
+ "model.layers.28",
72
+ "model.layers.29",
73
+ "model.layers.30",
74
+ "model.layers.31",
75
+ "model.layers.32",
76
+ "model.layers.33",
77
+ "model.layers.34",
78
+ "model.layers.35",
79
+ "model.layers.36",
80
+ "model.layers.37",
81
+ "model.layers.38",
82
+ "model.layers.39",
83
+ "model.layers.40",
84
+ "model.layers.41",
85
+ "model.layers.42",
86
+ "model.layers.43",
87
+ "model.layers.44",
88
+ "model.layers.45",
89
+ "model.layers.46",
90
+ "model.layers.47",
91
+ "model.layers.48",
92
+ "model.layers.49",
93
+ "model.layers.50",
94
+ "model.layers.51",
95
+ "model.layers.52",
96
+ "model.layers.53",
97
+ "model.layers.54",
98
+ "model.layers.55",
99
+ "model.layers.56",
100
+ "model.layers.57",
101
+ "model.layers.58",
102
+ "model.layers.59",
103
+ "model.layers.60",
104
+ "model.layers.61",
105
+ "model.layers.62",
106
+ "model.layers.63"
107
+ ]
108
+ ],
109
+ "true_sequential": false
110
+ },
111
+ "rms_norm_eps": 1e-05,
112
+ "rope_scaling": null,
113
+ "rope_theta": 1000000.0,
114
+ "sliding_window": null,
115
+ "tie_word_embeddings": false,
116
+ "torch_dtype": "float16",
117
+ "transformers_version": "4.46.3",
118
+ "use_cache": true,
119
+ "use_sliding_window": false,
120
+ "vocab_size": 152064
121
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.46.3"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f235557783084527b1eddbbc1fab48615f4dd49d5db7b55de4fe259101e2b41
3
+ size 4961918088
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96266b9de497d2f03c9bfe29448e0297d2f7e38f190551fd64a9fe123790a886
3
+ size 4987142120
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f05bc34a7c3e9985a9691465671cd3a30e9635ffd0a68e05c53891251e17c1
3
+ size 4981582472
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e462990317370cc6d6d9ffd39b2d6a916936c1e952229b32bd9278a7c6cd578d
3
+ size 4421758448
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quantize_config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "sym": true,
5
+ "data_type": "int",
6
+ "enable_quanted_input": true,
7
+ "enable_minmax_tuning": true,
8
+ "seqlen": 2048,
9
+ "batch_size": 1,
10
+ "scale_dtype": "torch.float16",
11
+ "lr": 0.001953125,
12
+ "minmax_lr": 0.001953125,
13
+ "gradient_accumulate_steps": 1,
14
+ "iters": 512,
15
+ "amp": true,
16
+ "nsamples": 128,
17
+ "low_gpu_mem_usage": true,
18
+ "to_quant_block_names": [
19
+ [
20
+ "model.layers.0",
21
+ "model.layers.1",
22
+ "model.layers.2",
23
+ "model.layers.3",
24
+ "model.layers.4",
25
+ "model.layers.5",
26
+ "model.layers.6",
27
+ "model.layers.7",
28
+ "model.layers.8",
29
+ "model.layers.9",
30
+ "model.layers.10",
31
+ "model.layers.11",
32
+ "model.layers.12",
33
+ "model.layers.13",
34
+ "model.layers.14",
35
+ "model.layers.15",
36
+ "model.layers.16",
37
+ "model.layers.17",
38
+ "model.layers.18",
39
+ "model.layers.19",
40
+ "model.layers.20",
41
+ "model.layers.21",
42
+ "model.layers.22",
43
+ "model.layers.23",
44
+ "model.layers.24",
45
+ "model.layers.25",
46
+ "model.layers.26",
47
+ "model.layers.27",
48
+ "model.layers.28",
49
+ "model.layers.29",
50
+ "model.layers.30",
51
+ "model.layers.31",
52
+ "model.layers.32",
53
+ "model.layers.33",
54
+ "model.layers.34",
55
+ "model.layers.35",
56
+ "model.layers.36",
57
+ "model.layers.37",
58
+ "model.layers.38",
59
+ "model.layers.39",
60
+ "model.layers.40",
61
+ "model.layers.41",
62
+ "model.layers.42",
63
+ "model.layers.43",
64
+ "model.layers.44",
65
+ "model.layers.45",
66
+ "model.layers.46",
67
+ "model.layers.47",
68
+ "model.layers.48",
69
+ "model.layers.49",
70
+ "model.layers.50",
71
+ "model.layers.51",
72
+ "model.layers.52",
73
+ "model.layers.53",
74
+ "model.layers.54",
75
+ "model.layers.55",
76
+ "model.layers.56",
77
+ "model.layers.57",
78
+ "model.layers.58",
79
+ "model.layers.59",
80
+ "model.layers.60",
81
+ "model.layers.61",
82
+ "model.layers.62",
83
+ "model.layers.63"
84
+ ]
85
+ ],
86
+ "enable_norm_bias_tuning": false,
87
+ "autoround_version": "0.4.1",
88
+ "quant_method": "gptq",
89
+ "desc_act": false,
90
+ "true_sequential": false,
91
+ "damp_percent": 0.01
92
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:913950e4971737031da511cdd1b410daae4566f62eb845b3975bca5a102323d8
3
+ size 11421995
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 32768,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff