Upload tiny models for BlenderbotSmallForCausalLM
Browse files- .gitattributes +1 -0
- config.json +35 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer_config.json +11 -0
- vocab.json +3 -0
.gitattributes
CHANGED
|
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
vocab.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BlenderbotSmallForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"classifier_dropout": 0.0,
|
| 10 |
+
"d_model": 16,
|
| 11 |
+
"decoder_attention_heads": 4,
|
| 12 |
+
"decoder_ffn_dim": 4,
|
| 13 |
+
"decoder_layerdrop": 0.0,
|
| 14 |
+
"decoder_layers": 2,
|
| 15 |
+
"decoder_start_token_id": 1,
|
| 16 |
+
"dropout": 0.1,
|
| 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": null,
|
| 23 |
+
"init_std": 0.02,
|
| 24 |
+
"is_decoder": true,
|
| 25 |
+
"is_encoder_decoder": false,
|
| 26 |
+
"max_position_embeddings": 20,
|
| 27 |
+
"model_type": "blenderbot-small",
|
| 28 |
+
"num_hidden_layers": 2,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"scale_embedding": false,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.25.0.dev0",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 54944
|
| 35 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab52ce17be8cbc9471b4653fed863bc1e9672fdec53a14179330595f9d34275e
|
| 3 |
+
size 3555033
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "__start__",
|
| 3 |
+
"eos_token": "__end__",
|
| 4 |
+
"pad_token": "__null__",
|
| 5 |
+
"unk_token": "__unk__"
|
| 6 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "__start__",
|
| 3 |
+
"eos_token": "__end__",
|
| 4 |
+
"model_max_length": 20,
|
| 5 |
+
"name_or_path": "facebook/blenderbot_small-90M",
|
| 6 |
+
"pad_token": "__null__",
|
| 7 |
+
"special_tokens_map_file": null,
|
| 8 |
+
"tokenizer_class": "BlenderbotSmallTokenizer",
|
| 9 |
+
"tokenizer_file": null,
|
| 10 |
+
"unk_token": "__unk__"
|
| 11 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f62b5ea937ea5d89b528766dbaa756ac0ed05fe8e8ee6fc0181fc143e7ffb4f7
|
| 3 |
+
size 991656
|