hf-transformers-bot commited on
Commit
253dd1f
·
verified ·
1 Parent(s): da9de0f

Update tiny models for OlmoForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OlmoForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "bos_token_id": null,
9
+ "clip_qkv": null,
10
+ "dtype": "float32",
11
+ "eos_token_id": 50279,
12
+ "hidden_act": "silu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 32,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 37,
17
+ "is_decoder": true,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "olmo",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 2,
22
+ "num_key_value_heads": 4,
23
+ "pad_token_id": 1,
24
+ "rope_parameters": {
25
+ "rope_theta": 10000.0,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": false,
29
+ "transformers_version": "5.16.0.dev0",
30
+ "type_vocab_size": 16,
31
+ "use_cache": true,
32
+ "vocab_size": 50280
33
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 50279,
4
+ "output_attentions": false,
5
+ "output_hidden_states": false,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "5.16.0.dev0",
8
+ "use_cache": true
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e8c82ccfb78ed81ec661dffa1aaf9faac647476c9fbc5c8350354b4691a8521
3
+ size 12934576
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "is_local": true,
9
+ "local_files_only": false,
10
+ "model_max_length": 512,
11
+ "pad_token": "<|padding|>",
12
+ "tokenizer_class": "GPTNeoXTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": null
15
+ }