OsakanaTeishoku commited on
Commit
e976f0a
1 Parent(s): ab2c4e7

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +30 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "None",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2400,
13
+ "max_position_embeddings": 131072,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 16,
16
+ "num_experts_per_tok": 1,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 2,
20
+ "output_router_logits": true,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": 1024,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.1",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }