jackkira commited on
Commit
e4b4c14
1 Parent(s): df23a7d

Upload OPTForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +54 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "batch_size": 1,
28
+ "bits": 4,
29
+ "block_name_to_quantize": "model.decoder.layers",
30
+ "damp_percent": 0.1,
31
+ "dataset": "c4",
32
+ "desc_act": false,
33
+ "disable_exllama": false,
34
+ "group_size": 128,
35
+ "max_input_length": null,
36
+ "model_seqlen": 2048,
37
+ "module_name_preceding_first_block": [
38
+ "model.decoder.embed_tokens",
39
+ "model.decoder.embed_positions",
40
+ "model.decoder.final_layer_norm"
41
+ ],
42
+ "pad_token_id": null,
43
+ "quant_method": "gptq",
44
+ "sym": true,
45
+ "tokenizer": null,
46
+ "true_sequential": true,
47
+ "use_cuda_fp16": true
48
+ },
49
+ "torch_dtype": "float16",
50
+ "transformers_version": "4.34.1",
51
+ "use_cache": true,
52
+ "vocab_size": 50272,
53
+ "word_embed_proj_dim": 768
54
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.34.1"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1de82f1f83cd8ec1e9954ace55ce0a06f75ff0c4ee7fd2ea1ccda15808728a9
3
+ size 125207098