at676 commited on
Commit
c4ba2db
1 Parent(s): 92b8180

2292b2a6306bbd4ca4ab59c75c72ce69beb8789cab94e5e6567da841154bcd5c

Browse files
Files changed (2) hide show
  1. config.json +40 -0
  2. generation_config.json +10 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-13b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pretraining_tp": 1,
19
+ "quip_params": {
20
+ "codebook": "E8P12RVQ4B",
21
+ "codebook_version": 1,
22
+ "codesz": 8,
23
+ "fused": true,
24
+ "idx_dtype": "torch.int64",
25
+ "lora_rank": 0,
26
+ "model_version": 1,
27
+ "outlier_channel_split": false,
28
+ "packsz": 2,
29
+ "rescale_WH": false,
30
+ "resid_scale_override": 3.45
31
+ },
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 10000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.34.0",
38
+ "use_cache": true,
39
+ "vocab_size": 32000
40
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.34.0"
10
+ }