crcdng commited on
Commit
3af4bfc
·
verified ·
1 Parent(s): dd47754

Upload config.json

Browse files

copy config.json from upstream model

Files changed (1) hide show
  1. config.json +37 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 960,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2560,
13
+ "is_llama_config": true,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 15,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 5,
20
+ "pad_token_id": 2,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_interleaved": false,
24
+ "rope_scaling": null,
25
+ "rope_theta": 100000,
26
+ "tie_word_embeddings": true,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.42.3",
29
+ "transformers.js_config": {
30
+ "kv_cache_dtype": {
31
+ "q4f16": "float16",
32
+ "fp16": "float16"
33
+ }
34
+ },
35
+ "use_cache": true,
36
+ "vocab_size": 49152
37
+ }