Update tiny models for CpmAntModel
Browse files- config.json +24 -0
- model.safetensors +3 -0
- tokenizer_config.json +66 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CpmAntModel"
|
| 4 |
+
],
|
| 5 |
+
"dim_ff": 37,
|
| 6 |
+
"dim_head": 128,
|
| 7 |
+
"dropout_p": 0.0,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eps": 1e-06,
|
| 10 |
+
"hidden_size": 32,
|
| 11 |
+
"init_std": 0.02,
|
| 12 |
+
"model_type": "cpmant",
|
| 13 |
+
"num_attention_heads": 4,
|
| 14 |
+
"num_hidden_layers": 2,
|
| 15 |
+
"position_bias_max_distance": 128,
|
| 16 |
+
"position_bias_num_buckets": 32,
|
| 17 |
+
"prompt_length": 8,
|
| 18 |
+
"prompt_types": 8,
|
| 19 |
+
"segment_types": 8,
|
| 20 |
+
"tie_word_embeddings": true,
|
| 21 |
+
"transformers_version": "5.16.0.dev0",
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 30720
|
| 24 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc1bcb0d13ad2051aaecc1ca02c16461e4658b148f112406d4e5e7bd0b32f6d4
|
| 3 |
+
size 4498752
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"6": {
|
| 20 |
+
"content": "<s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"7": {
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"8": {
|
| 36 |
+
"content": "<d>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"9": {
|
| 44 |
+
"content": "</d>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"backend": "custom",
|
| 53 |
+
"bod_token": "<d>",
|
| 54 |
+
"bos_token": "<s>",
|
| 55 |
+
"eod_token": "</d>",
|
| 56 |
+
"eos_token": "</s>",
|
| 57 |
+
"is_local": false,
|
| 58 |
+
"line_token": "</n>",
|
| 59 |
+
"local_files_only": false,
|
| 60 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 61 |
+
"pad_token": "<pad>",
|
| 62 |
+
"padding_side": "left",
|
| 63 |
+
"space_token": "</_>",
|
| 64 |
+
"tokenizer_class": "CpmAntTokenizer",
|
| 65 |
+
"unk_token": "<unk>"
|
| 66 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|