p1atdev commited on
Commit
deff08d
1 Parent(s): 7561bb4

Upload MixtralForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +31 -0
  2. generation_config.json +8 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "p1atdev/dart-v2-mixtral-160m",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "max_position_embeddings": 1024,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 8,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 4,
18
+ "num_key_value_heads": 1,
19
+ "num_local_experts": 4,
20
+ "output_router_logits": false,
21
+ "pad_token_id": 2,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_theta": 1000.0,
24
+ "router_aux_loss_coef": 0.02,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.38.2",
29
+ "use_cache": false,
30
+ "vocab_size": 30649
31
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.38.2",
7
+ "use_cache": false
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e610dc061daedac4705f3c6249d83bf7aff2d843e7bf0216d79ba899a10a98
3
+ size 331310944