Update tiny models for BlenderbotSmallForConditionalGeneration
Browse files- config.json +34 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- tokenizer_config.json +45 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BlenderbotSmallForConditionalGeneration"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"d_model": 16,
|
| 10 |
+
"decoder_attention_heads": 4,
|
| 11 |
+
"decoder_ffn_dim": 4,
|
| 12 |
+
"decoder_layerdrop": 0.0,
|
| 13 |
+
"decoder_layers": 2,
|
| 14 |
+
"decoder_start_token_id": 1,
|
| 15 |
+
"dropout": 0.1,
|
| 16 |
+
"dtype": "float32",
|
| 17 |
+
"encoder_attention_heads": 4,
|
| 18 |
+
"encoder_ffn_dim": 4,
|
| 19 |
+
"encoder_layerdrop": 0.0,
|
| 20 |
+
"encoder_layers": 2,
|
| 21 |
+
"eos_token_id": 2,
|
| 22 |
+
"forced_eos_token_id": 2,
|
| 23 |
+
"init_std": 0.02,
|
| 24 |
+
"is_decoder": false,
|
| 25 |
+
"is_encoder_decoder": true,
|
| 26 |
+
"max_position_embeddings": 200,
|
| 27 |
+
"model_type": "blenderbot-small",
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"scale_embedding": false,
|
| 30 |
+
"tie_word_embeddings": true,
|
| 31 |
+
"transformers_version": "5.16.0.dev0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 54944
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"decoder_start_token_id": 1,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 0,
|
| 10 |
+
"transformers_version": "5.16.0.dev0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b78bfe0cb852514a96d27545e8239aefba1e7d96080595fc55347c8be357a7c5
|
| 3 |
+
size 3801712
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "__null__",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "__start__",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "__end__",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "__unk__",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"backend": "custom",
|
| 37 |
+
"bos_token": "__start__",
|
| 38 |
+
"eos_token": "__end__",
|
| 39 |
+
"is_local": false,
|
| 40 |
+
"local_files_only": false,
|
| 41 |
+
"model_max_length": 200,
|
| 42 |
+
"pad_token": "__null__",
|
| 43 |
+
"tokenizer_class": "BlenderbotSmallTokenizer",
|
| 44 |
+
"unk_token": "__unk__"
|
| 45 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|