giulio98 commited on
Commit
7ad32d9
1 Parent(s): 30fa8b6

Upload CodeGenForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +41 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/codegen-350M-multi-xlcost-v2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "CodeGenForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "codegen",
14
+ "n_ctx": 2048,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 20,
19
+ "n_positions": 2048,
20
+ "resid_pdrop": 0.0,
21
+ "rotary_dim": 32,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "text-generation": {
30
+ "do_sample": true,
31
+ "max_length": 50,
32
+ "temperature": 1.0
33
+ }
34
+ },
35
+ "tie_word_embeddings": false,
36
+ "tokenizer_class": "GPT2Tokenizer",
37
+ "torch_dtype": "float16",
38
+ "transformers_version": "4.24.0",
39
+ "use_cache": false,
40
+ "vocab_size": 51200
41
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77dc65c8a0f70818a390bd9da83d391b024ac3f99743b473b282de659704ac69
3
+ size 797367631