morizon commited on
Commit
0666674
1 Parent(s): 8252be1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +147 -196
README.md CHANGED
@@ -1,199 +1,150 @@
1
  ---
2
- library_name: transformers
3
- tags: []
 
 
 
 
 
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
-
11
-
12
- ## Model Details
13
-
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
-
157
- [More Information Needed]
158
-
159
- ### Compute Infrastructure
160
-
161
- [More Information Needed]
162
-
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
-
189
- ## More Information [optional]
190
-
191
- [More Information Needed]
192
-
193
- ## Model Card Authors [optional]
194
-
195
- [More Information Needed]
196
-
197
- ## Model Card Contact
198
-
199
- [More Information Needed]
 
1
  ---
2
+ language: ja
3
+ license: apache-2.0
4
+ tags:
5
+ - text-generation
6
+ - transformers
7
+ - lora
8
+ model_name: llm-jp-3-13b_mix_30000_1209
9
+ base_model: llm-jp/llm-jp-3-13b
10
+ adapter_model: morizon/llm-jp-3-13b_mix_30000_1209
11
+ inference_framework: transformers
12
  ---
13
 
14
+ # モデル名
15
+ このモデルは日本語テキスト生成タスク向けに最適化されたLoRAアダプタ付きのモデルです。
16
+
17
+ ## 概要
18
+
19
+ #Sample Use
20
+
21
+ 以下は、elyza-tasks-100-TV_0.jsonl回答のためのコードです。
22
+
23
+ ```python
24
+
25
+ !pip install -U bitsandbytes
26
+ !pip install -U transformers
27
+ !pip install -U accelerate
28
+ !pip install -U datasets
29
+ !pip install -U peft
30
+
31
+ from transformers import (
32
+ AutoModelForCausalLM,
33
+ AutoTokenizer,
34
+ BitsAndBytesConfig,
35
+ )
36
+ from peft import PeftModel
37
+ import torch
38
+ from tqdm import tqdm
39
+ import json
40
+
41
+ # Hugging Faceで取得したTokenをこちらに貼る。
42
+ HF_TOKEN = "your_token"
43
+
44
+ # ベースとなるモデルと学習したLoRAのアダプタ。
45
+ model_id = "llm-jp/llm-jp-3-13b"
46
+
47
+ adapter_id = "morizon/llm-jp-3-13b_mix_30000_1209"
48
+
49
+ # QLoRA config
50
+ bnb_config = BitsAndBytesConfig(
51
+ load_in_4bit=True,
52
+ bnb_4bit_quant_type="nf4",
53
+ bnb_4bit_compute_dtype=torch.bfloat16,
54
+ )
55
+
56
+ # Load model
57
+ model = AutoModelForCausalLM.from_pretrained(
58
+ model_id,
59
+ quantization_config=bnb_config,
60
+ device_map="auto",
61
+ token = HF_TOKEN
62
+ )
63
+
64
+ # Load tokenizer
65
+ tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, token = HF_TOKEN)
66
+
67
+ # 元のモデルにLoRAのアダプタを統合。
68
+ model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
69
+
70
+ model.eval()
71
+
72
+ # データセットの読み込み。
73
+ # omnicampusの開発環境では、左にタスクのjsonlをドラッグアンドドロップしてから実行。
74
+ datasets = []
75
+ with open("./elyza-tasks-100-TV_0.jsonl", "r") as f:
76
+ item = ""
77
+ for line in f:
78
+ line = line.strip()
79
+ item += line
80
+ if item.endswith("}"):
81
+ datasets.append(json.loads(item))
82
+ item = ""
83
+
84
+
85
+ # システムプロンプト(固定の指示)
86
+ system_prompt = """
87
+ あなたはユーザが知りたいことを正確に把握し、的確に回答するアシスタントです。
88
+ 1. 指示に従う際は、必ずその内容を完全に理解し、結論を優先的に考慮するように心掛けてください。
89
+ 2. 問題の解答となる根拠は、常に文章内から探し出すようにして下さい。
90
+ 3. 指示から主要な情報と詳細を抽出し、要点を漏らさず回答することを重視して下さい。
91
+ 4. 回答のトーンやスタイルは、与えられたテーマや質問に合わせて柔軟に調整して下さい。
92
+ 5. 回答を作成した後は、必ず推敲を行い、誤りや曖昧さがないかどうか確認して下さい。
93
+ """
94
+
95
+ results = []
96
+
97
+ # データセットの処理
98
+ for data in tqdm(datasets):
99
+
100
+ input_text = data["input"]
101
+
102
+ # プロンプトの構築(システムプロンプト + ユーザー入力)
103
+ prompt = f"""### 指示
104
+ {system_prompt}
105
+
106
+ {input_text}
107
+ ### 回答
108
+ """
109
+
110
+ # トークナイズ
111
+ tokenized_input = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt").to(model.device)
112
+ attention_mask = torch.ones_like(tokenized_input)
113
+
114
+ # 推論パラメータの設定
115
+ max_new_tokens = 1024
116
+ do_sample = True
117
+ top_p = 0.95
118
+ temperature = 0.7
119
+ repetition_penalty = 1.05
120
+
121
+ # 推論実行
122
+ with torch.no_grad():
123
+ outputs = model.generate(
124
+ tokenized_input,
125
+ attention_mask=attention_mask, # attention_maskを明示的に指定
126
+ max_new_tokens=max_new_tokens,
127
+ do_sample=do_sample,
128
+ top_p=top_p,
129
+ temperature=temperature,
130
+ repetition_penalty=repetition_penalty,
131
+ pad_token_id=tokenizer.eos_token_id
132
+ )[0]
133
+
134
+ # 出力の整形
135
+ output = tokenizer.decode(outputs[tokenized_input.size(1):], skip_special_tokens=True)
136
+
137
+ # 結果を表示
138
+ print(f"Task ID: {data['task_id']}\nInput: {input_text}\nOutput: {output}\n{'-'*50}")
139
+
140
+ # 結果の保存
141
+ results.append({"task_id": data["task_id"], "input": input_text, "output": output})
142
+
143
+ import re
144
+ jsonl_id = re.sub(".*/", "", adapter_id)
145
+ with open(f"./{jsonl_id}-outputs_rev.jsonl", 'w', encoding='utf-8') as f:
146
+ for result in results:
147
+ json.dump(result, f, ensure_ascii=False) # ensure_ascii=False for handling non-ASCII characters
148
+ f.write('\n')
149
+
150
+ ```