Update tiny models for OPTForSequenceClassification
Browse files- config.json +30 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_remove_final_layer_norm": false,
|
| 3 |
+
"activation_function": "relu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"OPTForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"bos_token_id": 2,
|
| 9 |
+
"do_layer_norm_before": true,
|
| 10 |
+
"dropout": 0.1,
|
| 11 |
+
"dtype": "float32",
|
| 12 |
+
"embed_dim": 16,
|
| 13 |
+
"enable_bias": true,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"ffn_dim": 4,
|
| 16 |
+
"hidden_size": 16,
|
| 17 |
+
"init_std": 0.02,
|
| 18 |
+
"layer_norm_elementwise_affine": true,
|
| 19 |
+
"layerdrop": 0.0,
|
| 20 |
+
"max_position_embeddings": 200,
|
| 21 |
+
"model_type": "opt",
|
| 22 |
+
"num_attention_heads": 4,
|
| 23 |
+
"num_hidden_layers": 2,
|
| 24 |
+
"pad_token_id": 1,
|
| 25 |
+
"tie_word_embeddings": true,
|
| 26 |
+
"transformers_version": "5.16.0.dev0",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50265,
|
| 29 |
+
"word_embed_proj_dim": 16
|
| 30 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c1af630f09dea539850701a347665cfb574f40e0a8b5ea11e1f07d173ec8e54
|
| 3 |
+
size 3244536
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "</s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"is_local": true,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 200,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 12 |
+
"unk_token": "</s>"
|
| 13 |
+
}
|