hf-transformers-bot
commited on
Commit
•
b8c8d47
1
Parent(s):
45b60df
Upload tiny models for PersimmonModel
Browse files- .gitattributes +1 -0
- config.json +31 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +16 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +29 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"PersimmonModel"
|
4 |
+
],
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 71013,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout": 0.0,
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 32,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 37,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "persimmon",
|
18 |
+
"num_attention_heads": 4,
|
19 |
+
"num_hidden_layers": 2,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"partial_rotary_factor": 0.5,
|
22 |
+
"qk_layernorm": true,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 25000.0,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.34.0.dev0",
|
28 |
+
"type_vocab_size": 16,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 262144
|
31 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f57f55ee02bb31802e724aa0cac6300ef8df42805f32702e53109ee9da5669c4
|
3 |
+
size 33619610
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "|ENDOFTEXT|",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"unk_token": {
|
10 |
+
"content": "<unk>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
}
|
16 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40ca9f2afc67c230cfe5513fe038e3538a2f111cccf5c5aac82db24b63fbb884
|
3 |
+
size 16464024
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:407d001d18582959881b30ff39b660d4bd5ee50957d03f57daeeb3059e9db54c
|
3 |
+
size 6128796
|
tokenizer_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "|ENDOFTEXT|",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": null,
|
14 |
+
"legacy": null,
|
15 |
+
"model_max_length": 512,
|
16 |
+
"pad_token": null,
|
17 |
+
"sp_model_kwargs": {},
|
18 |
+
"spaces_between_special_tokens": false,
|
19 |
+
"tokenizer_class": "LlamaTokenizer",
|
20 |
+
"unk_token": {
|
21 |
+
"__type": "AddedToken",
|
22 |
+
"content": "<unk>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"use_default_system_prompt": true
|
29 |
+
}
|