Александр Олехнович
commited on
Commit
•
b675211
1
Parent(s):
35d08c8
Update from aleksandrolehnovic
Browse files- config.json +6 -0
- eval_results.txt +1 -1
- merges.txt +1 -1
- pytorch_model.bin +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
- vocab.json +0 -0
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"activation_function": "gelu_new",
|
3 |
"architectures": [
|
4 |
"GPT2LMHeadModel"
|
@@ -7,15 +8,18 @@
|
|
7 |
"bos_token_id": 50256,
|
8 |
"embd_pdrop": 0.1,
|
9 |
"eos_token_id": 50256,
|
|
|
10 |
"initializer_range": 0.02,
|
11 |
"layer_norm_epsilon": 1e-05,
|
12 |
"model_type": "gpt2",
|
13 |
"n_ctx": 1024,
|
14 |
"n_embd": 768,
|
15 |
"n_head": 12,
|
|
|
16 |
"n_layer": 12,
|
17 |
"n_positions": 1024,
|
18 |
"resid_pdrop": 0.1,
|
|
|
19 |
"summary_activation": null,
|
20 |
"summary_first_dropout": 0.1,
|
21 |
"summary_proj_to_labels": true,
|
@@ -26,5 +30,7 @@
|
|
26 |
"max_length": 1000
|
27 |
}
|
28 |
},
|
|
|
|
|
29 |
"vocab_size": 50257
|
30 |
}
|
1 |
{
|
2 |
+
"_name_or_path": "inspectorsolaris/gpt2_french",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPT2LMHeadModel"
|
8 |
"bos_token_id": 50256,
|
9 |
"embd_pdrop": 0.1,
|
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": 0.1,
|
22 |
+
"scale_attn_weights": true,
|
23 |
"summary_activation": null,
|
24 |
"summary_first_dropout": 0.1,
|
25 |
"summary_proj_to_labels": true,
|
30 |
"max_length": 1000
|
31 |
}
|
32 |
},
|
33 |
+
"transformers_version": "4.6.1",
|
34 |
+
"use_cache": true,
|
35 |
"vocab_size": 50257
|
36 |
}
|
eval_results.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
perplexity = tensor(
|
1 |
+
perplexity = tensor(9.3957)
|
merges.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
#version: 0.2
|
2 |
Ġ t
|
3 |
Ġ a
|
4 |
h e
|
1 |
+
#version: 0.2 - Trained by `huggingface/tokenizers`
|
2 |
Ġ t
|
3 |
Ġ a
|
4 |
h e
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510408315
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f464abebbbf76b340632ed2f73814d08424b3f72080a3a5049b8985f5d6e6db7
|
3 |
size 510408315
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{}
|
1 |
+
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": "cached/47f9d2df23101c315cce91981b7794d518df37d8646c790b73c0d186dbb7c287.3ae9ae72462581d20e36bc528e9c47bb30cd671bb21add40ca0b24a0be9fac22", "name_or_path": "inspectorsolaris/gpt2_french", "errors": "replace"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1327
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d484726aa46a03166701b70b8ca36eb9865dc9b1d27e916bcb99c83dfd3d2a4
|
3 |
size 1327
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|