This is the model that was made to solve Japanese tasks. It was fine-tuned by the data consisting of Japanese.
llmのための日本語インストラクションデータ作成 is the data. In detail,ichikawa-instruction-003-001-1, ichikara-instruction-003-001-2.1.json, ichikara-instruction-003-001-2.2.json, ichikara-instruction-003-001-5.1.json, ichikara-instruction-003-001-5.2.json are the data
In addition, this model has a following RAG function
MAX_TOKENS = 512
def classify_query(input_text):
"""クエリを分類して適切な指示を返す"""
if "理由" in input_text:
return "理由を順序だてて述べてください"
elif "方法" in input_text:
return "手順を具体的に説明してください"
else:
return "簡潔かつ正確に説明してください"
jsonl_id = "example_model_id" # モデルIDを指定
with open(f"./{jsonl_id}-outputs.jsonl", 'w', encoding='utf-8') as f:
for result in results:
filtered_result = {key: result[key] for key in ["task_id", "output"] if key in result}
json.dump(filtered_result, f, ensure_ascii=False)
f.write('\n')
Developed by: Taichi IGARASHI
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Finetuned from model [optional]: [More Information Needed]
Model Sources [optional]
Repository: [More Information Needed]
Paper [optional]: [More Information Needed]
Demo [optional]: [More Information Needed]
Uses
Direct Use
[More Information Needed]
Downstream Use [optional]
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
