dacorvo HF staff commited on
Commit
5f0c86e
1 Parent(s): 22458bc

Upload folder using huggingface_hub

Browse files
compiled/0dd8e2bcc93dcb98decd.neff ADDED
Binary file (677 kB). View file
 
compiled/12df8e791846fd44ac0d.neff ADDED
Binary file (749 kB). View file
 
compiled/57c15ebf0edcd6102e7b.neff ADDED
Binary file (656 kB). View file
 
compiled/9ed9f1a0b5f5f502397d.neff ADDED
Binary file (912 kB). View file
 
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "neuron": {
21
+ "auto_cast_type": "fp32",
22
+ "batch_size": 4,
23
+ "checkpoint_id": "gpt2",
24
+ "checkpoint_revision": "11c5a3d5811f50298f278a704980280950aedb10",
25
+ "compiler_type": "neuronx-cc",
26
+ "compiler_version": "2.12.68.0+4480452af",
27
+ "num_cores": 2,
28
+ "sequence_length": 1024,
29
+ "task": "text-generation"
30
+ },
31
+ "reorder_and_upcast_attn": false,
32
+ "resid_pdrop": 0.1,
33
+ "scale_attn_by_inverse_layer_idx": false,
34
+ "scale_attn_weights": true,
35
+ "summary_activation": null,
36
+ "summary_first_dropout": 0.1,
37
+ "summary_proj_to_labels": true,
38
+ "summary_type": "cls_index",
39
+ "summary_use_proj": true,
40
+ "task_specific_params": {
41
+ "text-generation": {
42
+ "do_sample": true,
43
+ "max_length": 50
44
+ }
45
+ },
46
+ "transformers_version": "4.36.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
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": "4.36.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "tokenizer_class": "GPT2Tokenizer",
18
+ "unk_token": "<|endoftext|>"
19
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff