angie-chen55 commited on
Commit
33f674b
1 Parent(s): f250a8b

upload model files

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {" ": 50282, " ": 50264, "\t\t\t\t\t\t\t": 50289, " ": 50280, " ": 50261, " ": 50260, " ": 50278, " ": 50284, " ": 50283, "\t\t\t\t\t\t\t\t\t": 50287, " ": 50272, " ": 50281, "\t\t\t\t": 50292, " ": 50266, " ": 50275, " ": 50262, " ": 50257, " ": 50276, " ": 50258, "\t\t\t\t\t": 50291, " ": 50269, "\t\t\t\t\t\t\t\t": 50288, " ": 50279, " ": 50274, " ": 50263, "\t\t\t": 50293, " ": 50268, " ": 50285, " ": 50286, " ": 50277, " ": 50265, " ": 50271, " ": 50270, "\t\t": 50294, " ": 50273, "\t\t\t\t\t\t": 50290, " ": 50259, " ": 50267}
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch/ac5968/code_gen/CodeGen/checkpoints/codegen-6B-mono",
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": 2,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "codegen",
15
+ "n_ctx": 2048,
16
+ "n_embd": 4096,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 33,
20
+ "n_positions": 2048,
21
+ "resid_pdrop": 0.0,
22
+ "rotary_dim": 64,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50,
33
+ "temperature": 1.0
34
+ }
35
+ },
36
+ "tokenizer_class": "GPT2Tokenizer",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.12.5",
39
+ "use_cache": true,
40
+ "vocab_size": 50295
41
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cd1195b733fcaad4591eefaebd1d146de185e4f365c4f2e1631be4f657e481c
3
+ size 28380568099
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": 50256}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad0e07a5efce1ae531ddc36f40ddb55f6db430d16918322fa81486e2a7af920b
3
+ size 3055
vocab.json ADDED
The diff for this file is too large to render. See raw diff