jlli commited on
Commit
47ded0c
1 Parent(s): 3e31b1d

ad4e70a72e1adce11078841b010adcc2222731762d12a32663dd778aca9736e0

Browse files
.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 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_residual_connection_post_layernorm": false,
3
+ "architectures": [
4
+ "BloomForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attention_softmax_in_fp32": true,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_dropout": 0.0,
11
+ "hidden_size": 14336,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "masked_softmax_fusion": true,
15
+ "model_type": "bloom",
16
+ "n_head": 112,
17
+ "n_layer": 70,
18
+ "pad_token_id": 3,
19
+ "pretraining_tp": 4,
20
+ "return_dict": false,
21
+ "slow_but_exact": false,
22
+ "transformers_version": "4.25.0",
23
+ "use_cache": true,
24
+ "vocab_size": 250880
25
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
3
+ size 14500443
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "bigscience/bloom",
7
+ "pad_token": "<pad>",
8
+ "padding_side": "left",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "BloomTokenizer",
11
+ "unk_token": "<unk>"
12
+ }