Merge branch 'main' of https://huggingface.co/MustEr/vgg_official
Browse files- config.json +2 -37
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
config.json
CHANGED
|
@@ -1,39 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 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 |
-
"initializer_range": 0.02,
|
| 12 |
-
"layer_norm_epsilon": 1e-05,
|
| 13 |
-
"model_type": "gpt2",
|
| 14 |
-
"n_ctx": 128,
|
| 15 |
-
"n_embd": 768,
|
| 16 |
-
"n_head": 12,
|
| 17 |
-
"n_inner": null,
|
| 18 |
-
"n_layer": 12,
|
| 19 |
-
"n_positions": 1024,
|
| 20 |
-
"reorder_and_upcast_attn": false,
|
| 21 |
-
"resid_pdrop": 0.1,
|
| 22 |
-
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
-
"scale_attn_weights": true,
|
| 24 |
-
"summary_activation": null,
|
| 25 |
-
"summary_first_dropout": 0.1,
|
| 26 |
-
"summary_proj_to_labels": true,
|
| 27 |
-
"summary_type": "cls_index",
|
| 28 |
-
"summary_use_proj": true,
|
| 29 |
-
"task_specific_params": {
|
| 30 |
-
"text-generation": {
|
| 31 |
-
"do_sample": true,
|
| 32 |
-
"max_length": 50
|
| 33 |
-
}
|
| 34 |
-
},
|
| 35 |
-
"torch_dtype": "float32",
|
| 36 |
-
"transformers_version": "4.31.0",
|
| 37 |
-
"use_cache": true,
|
| 38 |
-
"vocab_size": 50000
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"model_type": "tensorflow_h5",
|
| 3 |
+
"model_name_or_path": "tf_model.h5"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1024,
|
| 7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|