medmekk HF staff commited on
Commit
f814f41
·
verified ·
1 Parent(s): e9b2b7f

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. README.md +21 -0
  2. config.json +45 -0
  3. generation_config.json +6 -0
  4. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - gpt2
4
+ ---
5
+
6
+ # gpt2 (Quantized)
7
+
8
+ ## Description
9
+ This model is a quantized version of the original model `gpt2`. It has been quantized using int8_weight_only quantization with torchao.
10
+
11
+ ## Quantization Details
12
+ - **Quantization Type**: int8_weight_only
13
+ - **Group Size**: None
14
+
15
+ ## Usage
16
+ You can use this model in your applications by loading it directly from the Hugging Face Hub:
17
+
18
+ ```python
19
+ from transformers import AutoModel
20
+
21
+ model = AutoModel.from_pretrained("gpt2")
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "modules_to_not_convert": null,
22
+ "quant_method": "torchao",
23
+ "quant_type": "int8_weight_only",
24
+ "quant_type_kwargs": {}
25
+ },
26
+ "reorder_and_upcast_attn": false,
27
+ "resid_pdrop": 0.1,
28
+ "scale_attn_by_inverse_layer_idx": false,
29
+ "scale_attn_weights": true,
30
+ "summary_activation": null,
31
+ "summary_first_dropout": 0.1,
32
+ "summary_proj_to_labels": true,
33
+ "summary_type": "cls_index",
34
+ "summary_use_proj": true,
35
+ "task_specific_params": {
36
+ "text-generation": {
37
+ "do_sample": true,
38
+ "max_length": 50
39
+ }
40
+ },
41
+ "torch_dtype": "bfloat16",
42
+ "transformers_version": "4.46.0.dev0",
43
+ "use_cache": true,
44
+ "vocab_size": 50257
45
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.46.0.dev0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:088f4ab871f22574ab8b7eed7ff3e0a8d235ddf76d430acdd5663bc399eda64a
3
+ size 248925978