Hugging Face's logo

fbaldassarri
/
EleutherAI_pythia-70m-autogptq-int8-gs128-asym

Text Generation
Safetensors
PyTorch
English
gpt_neox
causal-lm
pythia
autoround
intel-autoround
auto-round
intel
woq
gptq
auto-gptq
autogptq
eleutheraI
8-bit precision
Model card Files
xet
Community
fbaldassarri commited on
Commit
665a0e3
·
verified ·
1 Parent(s): cac42a0

Initial Upload

Browse files
Files changed (8) hide show
  1. README.md +83 -0
  2. config.json +57 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
  5. quantize_config.json +25 -0
  6. special_tokens_map.json +23 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +215 -0
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ tags:
5
+ - pytorch
6
+ - causal-lm
7
+ - pythia
8
+ - autoround
9
+ - intel-autoround
10
+ - auto-round
11
+ - intel
12
+ - woq
13
+ - gptq
14
+ - auto-gptq
15
+ - autogptq
16
+ - eleutheraI
17
+ license: apache-2.0
18
+ model_name: Pythia 70m
19
+ base_model: EleutherAI/pythia-70m
20
+ inference: false
21
+ model_creator: EleutherAI
22
+ datasets:
23
+ - EleutherAI/pile
24
+ pipeline_tag: text-generation
25
+ prompt_template: '{prompt}
26
+ '
27
+ quantized_by: fbaldassarri
28
+ ---
29
+
30
+ ## Model Information
31
+
32
+ Quantized version of [EleutherAI/pythia-70m](https://huggingface.co/fbaldassarri/EleutherAI/pythia-70m) using torch.float32 for quantization tuning.
33
+ - 8 bits (INT8)
34
+ - group size = 128
35
+ - Asymmetrical Quantization
36
+ - Method AutoGPTQ
37
+
38
+ Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.5
39
+
40
+ Note: this INT8 version of pythia-70m has been quantized to run inference through CPU.
41
+
42
+ ## Replication Recipe
43
+
44
+ ### Step 1 Install Requirements
45
+
46
+ I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.
47
+
48
+ ```
49
+ wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.5.tar.gz
50
+ tar -xvzf v0.4.5.tar.gz
51
+ cd auto-round-0.4.5
52
+ pip install -r requirements-cpu.txt --upgrade
53
+ ```
54
+
55
+ ### Step 2 Build Intel AutoRound wheel from sources
56
+
57
+ ```
58
+ pip install -vvv --no-build-isolation -e .[cpu]
59
+ ```
60
+
61
+ ### Step 3 Script for Quantization
62
+
63
+ ```
64
+ from transformers import AutoModelForCausalLM, AutoTokenizer
65
+ model_name = "EleutherAI/pythia-70m"
66
+ model = AutoModelForCausalLM.from_pretrained(model_name)
67
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
68
+ from auto_round import AutoRound
69
+ bits, group_size, sym, device, amp = 8, 128, False, 'cpu', False
70
+ autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp)
71
+ autoround.quantize()
72
+ output_dir = "./AutoRound/EleutherAI_pythia-70m-autogptq-int8-gs128-asym"
73
+ autoround.save_quantized(output_dir, format='auto_gptq', inplace=True)
74
+ ```
75
+
76
+ ## License
77
+
78
+ [Apache 2.0 License](https://choosealicense.com/licenses/apache-2.0/)
79
+
80
+ ## Disclaimer
81
+
82
+ This quantized model comes with no warrenty. It has been developed only for research purposes.
83
+
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-70m",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 512,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2048,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 6,
21
+ "partial_rotary_factor": 0.25,
22
+ "quantization_config": {
23
+ "amp": false,
24
+ "autoround_version": "0.4.5",
25
+ "batch_size": 4,
26
+ "bits": 8,
27
+ "damp_percent": 0.01,
28
+ "data_type": "int",
29
+ "desc_act": false,
30
+ "enable_minmax_tuning": true,
31
+ "enable_norm_bias_tuning": false,
32
+ "enable_quanted_input": true,
33
+ "gradient_accumulate_steps": 1,
34
+ "group_size": 128,
35
+ "iters": 200,
36
+ "low_gpu_mem_usage": false,
37
+ "lr": 0.005,
38
+ "minmax_lr": 0.005,
39
+ "nsamples": 128,
40
+ "quant_method": "gptq",
41
+ "scale_dtype": "torch.float16",
42
+ "seqlen": 512,
43
+ "sym": false,
44
+ "to_quant_block_names": null,
45
+ "true_sequential": false
46
+ },
47
+ "rope_scaling": null,
48
+ "rope_theta": 10000,
49
+ "rotary_emb_base": 10000,
50
+ "rotary_pct": 0.25,
51
+ "tie_word_embeddings": false,
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.48.2",
54
+ "use_cache": true,
55
+ "use_parallel_residual": true,
56
+ "vocab_size": 50304
57
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.48.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d104ae4af1e926a77777083fcf8b90226b4afc112d06ae5b3ab599bc0e8bf19a
3
+ size 225573448
quantize_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 8,
3
+ "group_size": 128,
4
+ "sym": false,
5
+ "data_type": "int",
6
+ "enable_quanted_input": true,
7
+ "enable_minmax_tuning": true,
8
+ "seqlen": 512,
9
+ "batch_size": 4,
10
+ "scale_dtype": "torch.float16",
11
+ "lr": 0.005,
12
+ "minmax_lr": 0.005,
13
+ "gradient_accumulate_steps": 1,
14
+ "iters": 200,
15
+ "amp": false,
16
+ "nsamples": 128,
17
+ "low_gpu_mem_usage": false,
18
+ "to_quant_block_names": null,
19
+ "enable_norm_bias_tuning": false,
20
+ "autoround_version": "0.4.5",
21
+ "quant_method": "gptq",
22
+ "desc_act": false,
23
+ "true_sequential": false,
24
+ "damp_percent": 0.01
25
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ }
206
+ },
207
+ "bos_token": "<|endoftext|>",
208
+ "clean_up_tokenization_spaces": false,
209
+ "eos_token": "<|endoftext|>",
210
+ "extra_special_tokens": {},
211
+ "model_max_length": 1000000000000000019884624838656,
212
+ "pad_token": null,
213
+ "tokenizer_class": "GPTNeoXTokenizer",
214
+ "unk_token": "<|endoftext|>"
215
+ }