Text Generation
Transformers
Safetensors
mistral
conversational
text-generation-inference
pankajmathur commited on
Commit
3e35b73
·
verified ·
1 Parent(s): a0204e4

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +37 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MistralForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 12288,
13
+ "layer_types": [
14
+ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention",
15
+ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention",
16
+ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention",
17
+ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention",
18
+ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention",
19
+ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention",
20
+ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention",
21
+ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention",
22
+ "full_attention", "sliding_attention", "sliding_attention", "sliding_attention"
23
+ ],
24
+ "max_position_embeddings": 32768,
25
+ "model_type": "mistral",
26
+ "num_attention_heads": 32,
27
+ "num_hidden_layers": 36,
28
+ "num_key_value_heads": 8,
29
+ "rms_norm_eps": 1e-05,
30
+ "rope_theta": 100000000.0,
31
+ "sliding_window": 32768,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.46.0.dev0",
35
+ "use_cache": true,
36
+ "vocab_size": 131072
37
+ }