pigas commited on
Commit
df86fb1
1 Parent(s): ea1f97b

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +44 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-125m",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 3072,
16
+ "hidden_size": 768,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "quantization_config": {
27
+ "bits": 4,
28
+ "checkpoint_format": "gptq",
29
+ "damp_percent": 0.01,
30
+ "desc_act": false,
31
+ "group_size": 128,
32
+ "model_file_base_name": null,
33
+ "model_name_or_path": null,
34
+ "quant_method": "gptq",
35
+ "static_groups": false,
36
+ "sym": false,
37
+ "true_sequential": true
38
+ },
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.41.2",
41
+ "use_cache": true,
42
+ "vocab_size": 50272,
43
+ "word_embed_proj_dim": 768
44
+ }