smpanaro commited on
Commit
e059b48
1 Parent(s): c1101d6

Upload of AutoGPTQ quantized model

Browse files
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "quantization_config": {
21
+ "bits": 4,
22
+ "damp_percent": 0.01,
23
+ "desc_act": false,
24
+ "group_size": 128,
25
+ "is_marlin_format": false,
26
+ "model_file_base_name": "gptq_model-4bit-128g",
27
+ "model_name_or_path": "gpt2-4bit-128g",
28
+ "quant_method": "gptq",
29
+ "static_groups": false,
30
+ "sym": true,
31
+ "true_sequential": true
32
+ },
33
+ "reorder_and_upcast_attn": false,
34
+ "resid_pdrop": 0.1,
35
+ "scale_attn_by_inverse_layer_idx": false,
36
+ "scale_attn_weights": true,
37
+ "summary_activation": null,
38
+ "summary_first_dropout": 0.1,
39
+ "summary_proj_to_labels": true,
40
+ "summary_type": "cls_index",
41
+ "summary_use_proj": true,
42
+ "task_specific_params": {
43
+ "text-generation": {
44
+ "do_sample": true,
45
+ "max_length": 50
46
+ }
47
+ },
48
+ "torch_dtype": "float16",
49
+ "transformers_version": "4.37.2",
50
+ "use_cache": true,
51
+ "vocab_size": 50257
52
+ }
gptq_model-4bit-128g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41cfb2f48e5042ab5eff531b6233877272b493c3fb995b0ea62d71a90ebde38d
3
+ size 200619312
quantize_config.json 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": "gpt2-4bit-128g",
10
+ "model_file_base_name": "gptq_model-4bit-128g",
11
+ "is_marlin_format": false,
12
+ "quant_method": "gptq"
13
+ }