PetarStika commited on
Commit
29fae67
·
verified ·
1 Parent(s): 112b821

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OlmoForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "clip_qkv": 8.0,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 50279,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 4096,
16
+ "model_type": "olmo",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 16,
19
+ "num_key_value_heads": 16,
20
+ "pad_token_id": 1,
21
+ "rope_parameters": {
22
+ "rope_theta": 10000.0,
23
+ "rope_type": "default"
24
+ },
25
+ "tie_word_embeddings": false,
26
+ "transformers_version": "5.8.1",
27
+ "use_cache": true,
28
+ "vocab_size": 50304
29
+ }
eval_hellaswag_lume.json ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 50279,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "5.8.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a5de4ee6be34bf8c25b38644bb19b2cefc7b720d32c862284d0b0409879db5
3
+ size 2559587160
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
10
+ "max_length": 2048,
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "<|padding|>",
13
+ "stride": 0,
14
+ "tokenizer_class": "GPTNeoXTokenizer",
15
+ "trim_offsets": true,
16
+ "truncation_side": "right",
17
+ "truncation_strategy": "longest_first",
18
+ "unk_token": null
19
+ }