rootlocalghost commited on
Commit
bbcdc2c
·
verified ·
1 Parent(s): a87e376

clone pe/config.json

Browse files
Files changed (1) hide show
  1. pe/config.json +38 -0
pe/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Ministral3ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 1,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9216,
14
+ "max_position_embeddings": 262144,
15
+ "model_type": "ministral3",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 26,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 11,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_parameters": {
22
+ "beta_fast": 32.0,
23
+ "beta_slow": 1.0,
24
+ "factor": 16.0,
25
+ "llama_4_scaling_beta": 0.1,
26
+ "mscale": 1.0,
27
+ "mscale_all_dim": 1.0,
28
+ "original_max_position_embeddings": 16384,
29
+ "rope_theta": 1000000.0,
30
+ "rope_type": "yarn",
31
+ "type": "yarn"
32
+ },
33
+ "sliding_window": null,
34
+ "tie_word_embeddings": true,
35
+ "transformers_version": "5.3.0",
36
+ "use_cache": true,
37
+ "vocab_size": 131072
38
+ }