mapama247 commited on
Commit
bdc74dd
1 Parent(s): dfd733a

add config files

Browse files
Files changed (2) hide show
  1. config.json +30 -0
  2. generation_config.json +12 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/gpfs/projects/bsc88/text/models/instruction-tuning/models/base_models_with_special_tokens/bsc_2b_4thepoch_hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5440,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "num_layers": 24,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.40.2",
28
+ "use_cache": true,
29
+ "vocab_size": 256000
30
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2,
6
+ 5
7
+ ],
8
+ "do_sample": true,
9
+ "temperature": 0.6,
10
+ "repetition_penalty": 1.2,
11
+ "transformers_version": "4.40.2"
12
+ }