banghua commited on
Commit
ce092b3
1 Parent(s): 4f2a998

Upload 8 files

Browse files
added_tokens (2).json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|end_of_turn|>": 32000,
3
+ "<|pad_0|>": 32001
4
+ }
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "_name_or_path": "openchat/openchat-3.5-0106",
3
  "architectures": [
4
- "MistralModel"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
@@ -19,8 +19,8 @@
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.36.2",
24
  "use_cache": true,
25
  "vocab_size": 32002
26
  }
 
1
  {
2
+ "_name_or_path": "imone/Mistral_7B_with_EOT_token",
3
  "architectures": [
4
+ "MistralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
 
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.36.1",
24
  "use_cache": true,
25
  "vocab_size": 32002
26
  }
generation_config (1).json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "max_length": 8192,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.5,
8
+ "transformers_version": "4.35.2"
9
+ }
openchat (1).json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"local_rank": 0, "model_path": "imone/Mistral_7B_with_EOT_token", "data_prefix": "", "save_path": "", "save_every": 1, "batch_max_len": 77824, "epochs": 5, "lr": 1.1179251066632773e-05, "lr_min_ratio": 0.1, "lr_warmup_ratio": 0.05, "weight_decay": 0.1, "beta1": 0.9, "beta2": 0.95, "eps": 1e-05, "deepspeed": true, "deepspeed_config": "ochat/training_deepspeed/deepspeed_config.json", "deepscale": false, "deepscale_config": null, "deepspeed_mpi": false, "model_type": "openchat_v3.2_mistral", "device": "<non-serializable>", "epoch": 2}
special_tokens_map (2).json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "unk_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
tokenizer (3).model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config (2).json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|end_of_turn|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|pad_0|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<|end_of_turn|>",
48
+ "<|pad_0|>"
49
+ ],
50
+ "bos_token": "<s>",
51
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
52
+ "clean_up_tokenization_spaces": false,
53
+ "eos_token": "<|end_of_turn|>",
54
+ "legacy": true,
55
+ "model_max_length": 1000000000000000019884624838656,
56
+ "pad_token": null,
57
+ "sp_model_kwargs": {},
58
+ "spaces_between_special_tokens": false,
59
+ "tokenizer_class": "LlamaTokenizer",
60
+ "unk_token": "<unk>",
61
+ "use_default_system_prompt": true
62
+ }