Commit
•
4f84de3
1
Parent(s):
30d19aa
init
Browse files- .gitattributes +1 -0
- README.md +24 -0
- config.json +36 -0
- merges.txt +0 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -15,3 +15,4 @@
|
|
15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
17 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
17 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
18 |
+
.h5 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Model card for RoGPT2-base
|
2 |
+
|
3 |
+
---
|
4 |
+
language:
|
5 |
+
- ro
|
6 |
+
---
|
7 |
+
|
8 |
+
# RoGPT2: Romanian GPT2 for text generation
|
9 |
+
|
10 |
+
All models are available:
|
11 |
+
* [RoBERT-base](https://huggingface.co/readerbench/RoGPT2-base)
|
12 |
+
* [RoBERT-medium](https://huggingface.co/readerbench/RoGPT2-medium)
|
13 |
+
* [RoBERT-large](https://huggingface.co/readerbench/RoGPT2-large)
|
14 |
+
|
15 |
+
#### How to use
|
16 |
+
```python
|
17 |
+
~~from transformers import AutoTokenizer, TFAutoModelWithLMHead
|
18 |
+
|
19 |
+
tokenizer = AutoTokenizer.from_pretrained('readerbench/RoGPT2-base')
|
20 |
+
model = TFAutoModelWithLMHead.from_pretrained('readerbench/RoGPT2-base')
|
21 |
+
inputs = tokenizer.encode("Este o zi de vara", return_tensors='tf')
|
22 |
+
text = model.generate(inputs, max_length=1024, no_repeat_ngram_size=2)
|
23 |
+
print(tokenizer.decode(text[0]))~~
|
24 |
+
```
|
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "model/base",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 0,
|
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 |
+
"summary_activation": null,
|
23 |
+
"summary_first_dropout": 0.1,
|
24 |
+
"summary_proj_to_labels": true,
|
25 |
+
"summary_type": "cls_index",
|
26 |
+
"summary_use_proj": true,
|
27 |
+
"task_specific_params": {
|
28 |
+
"text-generation": {
|
29 |
+
"do_sample": true,
|
30 |
+
"max_length": 50
|
31 |
+
}
|
32 |
+
},
|
33 |
+
"transformers_version": "4.5.1",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50257
|
36 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:433a00b42261edcb8a415b3ffb3a9f84ca8eb5ae79ae4ec5d4355a28db08e56b
|
3 |
+
size 497933648
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "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": null, "tokenizer_file": null, "name_or_path": "tokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|