pytorch model
Browse files- added_tokens.json +1 -0
- config.json +2 -0
- flax_to_torch.py +8 -0
- merges.txt +0 -0
- nohup.out +2 -2
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<|endoftext|>": 50265}
|
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"activation_function": "gelu_new",
|
3 |
"architectures": [
|
4 |
"GPT2LMHeadModel"
|
@@ -30,6 +31,7 @@
|
|
30 |
"max_length": 50
|
31 |
}
|
32 |
},
|
|
|
33 |
"transformers_version": "4.9.0.dev0",
|
34 |
"use_cache": true,
|
35 |
"vocab_size": 50257
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
|
|
31 |
"max_length": 50
|
32 |
}
|
33 |
},
|
34 |
+
"torch_dtype": "float32",
|
35 |
"transformers_version": "4.9.0.dev0",
|
36 |
"use_cache": true,
|
37 |
"vocab_size": 50257
|
flax_to_torch.py
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import GPT2LMHeadModel, AutoTokenizer
|
2 |
+
|
3 |
+
model = GPT2LMHeadModel.from_pretrained("./", from_flax=True)
|
4 |
+
model.save_pretrained("./")
|
5 |
+
|
6 |
+
tokenizer = AutoTokenizer.from_pretrained("./")
|
7 |
+
tokenizer.save_pretrained("./")
|
8 |
+
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
nohup.out
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cade874a9849a5d9d43c55bbf8125aaf61871c48e107794c3d40f25d3da1a3e6
|
3 |
+
size 2980551
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0691a41897b2759e59f2c34c00c20b1534726950c84127b56073c4687a8560e
|
3 |
+
size 510401385
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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
ADDED
The diff for this file is too large to render.
See raw diff
|
|