Trouter-Library commited on
Commit
6fffac2
·
verified ·
1 Parent(s): d25c5f6

Create config.json

Browse files
Files changed (1) hide show
  1. config.json +43 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "DeepXR/Helion-2.5-Rnd",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
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": 131072,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": {
22
+ "factor": 8.0,
23
+ "original_max_position_embeddings": 16384,
24
+ "type": "yarn"
25
+ },
26
+ "rope_theta": 500000.0,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.40.0",
30
+ "use_cache": true,
31
+ "vocab_size": 128256,
32
+ "pad_token_id": 128001,
33
+ "mlp_bias": false,
34
+ "head_dim": 128,
35
+ "quantization_config": {
36
+ "load_in_8bit": false,
37
+ "load_in_4bit": false
38
+ },
39
+ "auto_map": {
40
+ "AutoConfig": "configuration_llama.LlamaConfig",
41
+ "AutoModelForCausalLM": "modeling_llama.LlamaForCausalLM"
42
+ }
43
+ }