Safetensors
gemma2
kirigayahitsugi commited on
Commit
8a3569a
1 Parent(s): 3190e0e

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +36 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/cephfs/shared/hf_cache/hub/models--google--gemma-2-2b-it/snapshots/299a8560bedf22ed1c72a8a11e7dce4a7f9f51f8",
3
+ "architectures": [
4
+ "CustomRewardModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": 50.0,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": [
12
+ 1,
13
+ 107
14
+ ],
15
+ "final_logit_softcapping": 30.0,
16
+ "head_dim": 256,
17
+ "hidden_act": "gelu_pytorch_tanh",
18
+ "hidden_activation": "gelu_pytorch_tanh",
19
+ "hidden_size": 2304,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 9216,
22
+ "max_position_embeddings": 8192,
23
+ "model_type": "gemma2",
24
+ "num_attention_heads": 8,
25
+ "num_hidden_layers": 26,
26
+ "num_key_value_heads": 4,
27
+ "pad_token_id": 0,
28
+ "query_pre_attn_scalar": 256,
29
+ "rms_norm_eps": 1e-06,
30
+ "rope_theta": 10000.0,
31
+ "sliding_window": 4096,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.43.4",
34
+ "use_cache": true,
35
+ "vocab_size": 256000
36
+ }