xxx777xxxASD commited on
Commit
c1b0b5e
1 Parent(s): b75c270

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +35 -35
config.json CHANGED
@@ -1,35 +1,35 @@
1
- {
2
- "_name_or_path": "NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS",
3
- "architectures": [
4
- "MixtralForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128001,
10
- "hidden_act": "silu",
11
- "hidden_size": 4096,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
15
- "mlp_bias": false,
16
- "model_type": "mixtral",
17
- "num_attention_heads": 32,
18
- "num_experts_per_tok": 2,
19
- "num_hidden_layers": 32,
20
- "num_key_value_heads": 8,
21
- "num_local_experts": 4,
22
- "output_router_logits": false,
23
- "pretraining_tp": 1,
24
- "rms_norm_eps": 1e-05,
25
- "rope_scaling": null,
26
- "rope_theta": 500000.0,
27
- "router_aux_loss_coef": 0.001,
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": true,
34
- "vocab_size": 128256
35
- }
 
1
+ {
2
+ "_name_or_path": "NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "mixtral",
17
+ "num_attention_heads": 32,
18
+ "num_experts_per_tok": 2,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "num_local_experts": 4,
22
+ "output_router_logits": false,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 500000.0,
27
+ "router_aux_loss_coef": 0.001,
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": true,
34
+ "vocab_size": 128256
35
+ }