LlamaFinetuneBase commited on
Commit
645e60e
1 Parent(s): 65c439a

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +33 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma2ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": 50.0,
8
+ "bos_token_id": 2,
9
+ "cache_implementation": "hybrid",
10
+ "eos_token_id": 1,
11
+ "final_logit_softcapping": 30.0,
12
+ "head_dim": 256,
13
+ "hidden_act": "gelu_pytorch_tanh",
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 3584,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 8192,
19
+ "model_type": "gemma2",
20
+ "num_attention_heads": 16,
21
+ "num_hidden_layers": 42,
22
+ "num_key_value_heads": 8,
23
+ "pad_token_id": 0,
24
+ "query_pre_attn_scalar": 256,
25
+ "rms_norm_eps": 1e-06,
26
+ "rope_theta": 10000.0,
27
+ "sliding_window": 4096,
28
+ "sliding_window_size": 4096,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.42.0.dev0",
31
+ "use_cache": true,
32
+ "vocab_size": 256000
33
+ }