TenzinGayche commited on
Commit
e14ce5a
·
verified ·
1 Parent(s): f771118

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +36 -0
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tmp/gemma2/step_21600/model",
3
+ "architectures": [
4
+ "Gemma2ForCausalLM"
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": 1,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 256,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 3584,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "max_input_length": 2048,
20
+ "max_length": null,
21
+ "max_position_embeddings": 8192,
22
+ "model_type": "gemma2",
23
+ "num_attention_heads": 16,
24
+ "num_hidden_layers": 42,
25
+ "num_key_value_heads": 8,
26
+ "pad_token_id": 0,
27
+ "query_pre_attn_scalar": 224,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_theta": 10000.0,
30
+ "sliding_window": 4096,
31
+ "sliding_window_size": 4096,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.46.0",
34
+ "use_cache": true,
35
+ "vocab_size": 256000
36
+ }