ybelkada commited on
Commit
746eaa3
1 Parent(s): 34cfdfd

Upload MixtralForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +28 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/younes/code/new-model-addition/converted-small-mixtral",
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": 3584,
13
+ "max_position_embeddings": 131072,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 2,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_theta": 10000.0,
22
+ "sliding_window": 4096,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.36.0.dev0",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.0.dev0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a18e5d30b9f1dd74c5d94cea9dd3a2626b946242311a488ffd5b11f08300ba4
3
+ size 493930304