Yixin Song commited on
Commit
e181620
1 Parent(s): c1178d9
Files changed (1) hide show
  1. config.json +35 -0
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SuperSparseMixtralForCausalLM"
4
+ ],
5
+ "auto_map": {
6
+ "AutoConfig": "configuration_supersparsemixtral.SuperSparseMixtralConfig",
7
+ "AutoModel": "modeling_supersparsemixtral.SuperSparseMixtralForCausalLM",
8
+ "AutoModelForCausalLM": "modeling_supersparsemixtral.SuperSparseMixtralForCausalLM"
9
+ },
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_act": "relu",
14
+ "hidden_size": 4096,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 14336,
17
+ "max_position_embeddings": 32768,
18
+ "model_type": "mixtral",
19
+ "num_attention_heads": 32,
20
+ "num_experts_per_tok": 2,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 8,
23
+ "num_local_experts": 8,
24
+ "output_router_logits": true,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_theta": 1000000.0,
27
+ "router_aux_loss_coef": 0.02,
28
+ "router_jitter_noise": 0.0,
29
+ "sliding_window": null,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.41.0",
33
+ "use_cache": false,
34
+ "vocab_size": 57024
35
+ }