Galuh commited on
Commit
ff4b7e2
1 Parent(s): 712920e
added_tokens.json DELETED
@@ -1 +0,0 @@
1
- {"<|endoftext|>": 50257}
 
 
config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "_name_or_path": ".",
3
- "activation_function": "gelu_new",
4
- "architectures": [
5
- "GPT2LMHeadModel"
6
- ],
7
- "attn_pdrop": 0.0,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.0,
10
- "eos_token_id": 50256,
11
- "gradient_checkpointing": false,
12
- "initializer_range": 0.02,
13
- "layer_norm_epsilon": 1e-05,
14
- "model_type": "gpt2",
15
- "n_ctx": 1024,
16
- "n_embd": 768,
17
- "n_head": 12,
18
- "n_inner": null,
19
- "n_layer": 12,
20
- "n_positions": 1024,
21
- "resid_pdrop": 0.0,
22
- "scale_attn_weights": true,
23
- "summary_activation": null,
24
- "summary_first_dropout": 0.1,
25
- "summary_proj_to_labels": true,
26
- "summary_type": "cls_index",
27
- "summary_use_proj": true,
28
- "task_specific_params": {
29
- "text-generation": {
30
- "do_sample": true,
31
- "max_length": 50
32
- }
33
- },
34
- "torch_dtype": "float32",
35
- "transformers_version": "4.10.0.dev0",
36
- "use_cache": true,
37
- "vocab_size": 50257
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:60adedef3fa1ea0b88397f273516fddf2842b7f2d2b8fb692b444badaf374166
3
- size 497764120
 
 
 
 
jax2torch.py DELETED
@@ -1,15 +0,0 @@
1
- from transformers import AutoTokenizer, GPT2LMHeadModel
2
-
3
- '''
4
-
5
- This is a script to convert the Jax model and the tokenizer to Pytorch model
6
-
7
- '''
8
-
9
- model = GPT2LMHeadModel.from_pretrained(".", from_flax=True)
10
-
11
- model.save_pretrained(".")
12
-
13
- tokenizer = AutoTokenizer.from_pretrained(".")
14
-
15
- tokenizer.save_pretrained(".")
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a666f9ef05f74e013906270b94ba69cee50988d12309160e5c5e4a724893d979
3
- size 510401385
 
 
 
 
special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
 
 
tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": ".", "tokenizer_class": "GPT2Tokenizer"}
 
 
vocab.json DELETED
The diff for this file is too large to render. See raw diff