Yash0109 commited on
Commit
aefc7be
1 Parent(s): 1b3afdc

diaratechHf_llama

Browse files
README.md CHANGED
@@ -1,14 +1,13 @@
1
  ---
2
- license: mit
3
  library_name: peft
4
  tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
- base_model: microsoft/Phi-3-mini-128k-instruct
9
  datasets:
10
  - generator
11
- pipeline_tag: text-generation
12
  model-index:
13
  - name: diaratechHf_llama
14
  results: []
@@ -19,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  # diaratechHf_llama
21
 
22
- This model is a fine-tuned version of [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) on the generator dataset.
23
 
24
  ## Model description
25
 
@@ -56,5 +55,5 @@ The following hyperparameters were used during training:
56
  - PEFT 0.10.0
57
  - Transformers 4.40.1
58
  - Pytorch 2.3.0+cu121
59
- - Datasets 2.19.0
60
  - Tokenizers 0.19.1
 
1
  ---
2
+ license: apache-2.0
3
  library_name: peft
4
  tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
9
  datasets:
10
  - generator
 
11
  model-index:
12
  - name: diaratechHf_llama
13
  results: []
 
18
 
19
  # diaratechHf_llama
20
 
21
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
 
23
  ## Model description
24
 
 
55
  - PEFT 0.10.0
56
  - Transformers 4.40.1
57
  - Pytorch 2.3.0+cu121
58
+ - Datasets 2.19.1
59
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -20,14 +20,14 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
- "k_proj",
25
- "lm_head",
26
  "up_proj",
27
  "q_proj",
28
- "o_proj",
29
  "gate_proj",
30
- "down_proj"
 
 
 
31
  ],
32
  "task_type": "CAUSAL_LM",
33
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "up_proj",
24
  "q_proj",
25
+ "k_proj",
26
  "gate_proj",
27
+ "lm_head",
28
+ "v_proj",
29
+ "down_proj",
30
+ "o_proj"
31
  ],
32
  "task_type": "CAUSAL_LM",
33
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:616a01d54a824d93443dfd652074149207b9b9a6f92cd3e9dd621dc297068cf0
3
- size 545621264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a2bbd9f6fe4508ac71d8932067f3598fa1797e2c0e56815e742224665b16c4
3
+ size 1204678496
special_tokens_map.json CHANGED
@@ -7,13 +7,13 @@
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|endoftext|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": 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": "</s>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -22,108 +22,21 @@
22
  "content": "</s>",
23
  "lstrip": false,
24
  "normalized": false,
25
- "rstrip": true,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "32000": {
30
- "content": "<|endoftext|>",
31
- "lstrip": false,
32
- "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
- },
37
- "32001": {
38
- "content": "<|assistant|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": true,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "32002": {
46
- "content": "<|placeholder1|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": true,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32003": {
54
- "content": "<|placeholder2|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": true,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "32004": {
62
- "content": "<|placeholder3|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": true,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "32005": {
70
- "content": "<|placeholder4|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": true,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "32006": {
78
- "content": "<|system|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": true,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "32007": {
86
- "content": "<|end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": true,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "32008": {
94
- "content": "<|placeholder5|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": true,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "32009": {
102
- "content": "<|placeholder6|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": true,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "32010": {
110
- "content": "<|user|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": true,
114
- "single_word": false,
115
- "special": true
116
  }
117
  },
 
118
  "bos_token": "<s>",
119
- "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
  "clean_up_tokenization_spaces": false,
121
- "eos_token": "<|endoftext|>",
122
- "legacy": false,
123
- "model_max_length": 131072,
124
- "pad_token": "<|endoftext|>",
125
- "padding_side": "right",
126
  "sp_model_kwargs": {},
 
127
  "tokenizer_class": "LlamaTokenizer",
128
  "unk_token": "<unk>",
129
  "use_default_system_prompt": false
 
22
  "content": "</s>",
23
  "lstrip": false,
24
  "normalized": false,
 
 
 
 
 
 
 
 
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  }
29
  },
30
+ "additional_special_tokens": [],
31
  "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
  "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
 
38
  "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
  "unk_token": "<unk>",
42
  "use_default_system_prompt": false
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6d723d5217803b087b5a3114f97a303aaf7c83fcf85c5234fe3b3ba9db45328
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b54ee5dfe7678e20a2032b08ad6d09aa31ce2f4e792a1de5c911588853f3dde5
3
  size 5048