TroyDoesAI commited on
Commit
b6d7079
·
verified ·
1 Parent(s): 236c76e

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +33 -33
config.json CHANGED
@@ -1,33 +1,33 @@
1
- {
2
- "_name_or_path": ".\\BlackSheep-MoE",
3
- "architectures": [
4
- "MixtralForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": null,
8
- "eos_token_id": 151645,
9
- "hidden_act": "silu",
10
- "hidden_size": 3584,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 18944,
13
- "max_position_embeddings": 32768,
14
- "max_window_layers": 28,
15
- "model_type": "mixtral",
16
- "num_attention_heads": 28,
17
- "num_experts_per_tok": 2,
18
- "num_hidden_layers": 20,
19
- "num_key_value_heads": 4,
20
- "num_local_experts": 2,
21
- "output_router_logits": false,
22
- "rms_norm_eps": 1e-06,
23
- "rope_theta": 1000000.0,
24
- "router_aux_loss_coef": 0.001,
25
- "router_jitter_noise": 0.0,
26
- "sliding_window": null,
27
- "tie_word_embeddings": false,
28
- "torch_dtype": "float16",
29
- "transformers_version": "4.41.2",
30
- "use_cache": false,
31
- "use_sliding_window": false,
32
- "vocab_size": 152064
33
- }
 
1
+ {
2
+ "_name_or_path": ".\\BlackSheep-MoE",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 28,
17
+ "num_experts_per_tok": 1,
18
+ "num_hidden_layers": 20,
19
+ "num_key_value_heads": 4,
20
+ "num_local_experts": 2,
21
+ "output_router_logits": false,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_theta": 1000000.0,
24
+ "router_aux_loss_coef": 0.001,
25
+ "router_jitter_noise": 0.0,
26
+ "sliding_window": null,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float16",
29
+ "transformers_version": "4.41.2",
30
+ "use_cache": false,
31
+ "use_sliding_window": false,
32
+ "vocab_size": 152064
33
+ }