Hugging Face's logo

dongsheng
/
DTA_llama2_7b

llama
Model card Files
xet
Community
dongsheng commited on
Commit
2abf59f
·
verified ·
1 Parent(s): 6b7ab91

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +26 -0
  2. generation_config.json +10 -0
  3. index.html +28 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +35 -0
  7. trainer_state.json +0 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/paddlejob/workspace/env_run/baidu/personal-code/tool_llama_client/initial_model/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.28.1",
24
+ "use_cache": false,
25
+ "vocab_size": 32000
26
+ }
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": "4.28.1"
10
+ }
index.html ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
2
+ <html>
3
+ <head>
4
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
5
+ <title>Directory listing for /train_7b_4ep_merg_train_single/</title>
6
+ </head>
7
+ <body>
8
+ <h1>Directory listing for /train_7b_4ep_merg_train_single/</h1>
9
+ <hr>
10
+ <ul>
11
+ <li><a href="checkpoint-2465/">checkpoint-2465/</a></li>
12
+ <li><a href="checkpoint-3284/">checkpoint-3284/</a></li>
13
+ <li><a href="config.json">config.json</a></li>
14
+ <li><a href="generation_config.json">generation_config.json</a></li>
15
+ <li><a href="pytorch_model-00001-of-00003.bin">pytorch_model-00001-of-00003.bin</a></li>
16
+ <li><a href="pytorch_model-00002-of-00003.bin">pytorch_model-00002-of-00003.bin</a></li>
17
+ <li><a href="pytorch_model-00003-of-00003.bin">pytorch_model-00003-of-00003.bin</a></li>
18
+ <li><a href="pytorch_model.bin.index.json">pytorch_model.bin.index.json</a></li>
19
+ <li><a href="runs/">runs/</a></li>
20
+ <li><a href="special_tokens_map.json">special_tokens_map.json</a></li>
21
+ <li><a href="tokenizer.model">tokenizer.model</a></li>
22
+ <li><a href="tokenizer_config.json">tokenizer_config.json</a></li>
23
+ <li><a href="trainer_state.json">trainer_state.json</a></li>
24
+ <li><a href="training_args.bin">training_args.bin</a></li>
25
+ </ul>
26
+ <hr>
27
+ </body>
28
+ </html>
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 8192,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b698a2f2b247f9933c38dca907255bd09d0d8cc760f0457289b27083cd4dd1e
3
+ size 4344