reach-vb HF staff commited on
Commit
1f8cb66
1 Parent(s): 11e7348

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +45 -0
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 576,
11
+ "initializer_range": 0.041666666666666664,
12
+ "intermediate_size": 1536,
13
+ "is_llama_config": true,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 9,
18
+ "num_hidden_layers": 30,
19
+ "num_key_value_heads": 3,
20
+ "pad_token_id": 2,
21
+ "pretraining_tp": 1,
22
+ "quantization": {
23
+ "group_size": 64,
24
+ "bits": 8
25
+ },
26
+ "quantization_config": {
27
+ "group_size": 64,
28
+ "bits": 8
29
+ },
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_interleaved": false,
32
+ "rope_scaling": null,
33
+ "rope_theta": 100000,
34
+ "tie_word_embeddings": true,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers.js_config": {
37
+ "kv_cache_dtype": {
38
+ "q4f16": "float16",
39
+ "fp16": "float16"
40
+ }
41
+ },
42
+ "transformers_version": "4.42.3",
43
+ "use_cache": true,
44
+ "vocab_size": 49152
45
+ }