Model Card for Model ID
Model Details
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
This is a LoRA-finetuned model based on Matsuo Lab's LoRA_template_20241127. The model has been fine-tuned for sequence classification with a reduced max_seq_length of 128 due to GPU constraints.
The model has been trained using the dataset ichikara-instruction-003-001-1.json.
- Developed by: Eisuke Dohi
- Funded by [optional]: None
- Shared by [optional]: Eisuke Dohi
- Model type: LoRA finetuned transformer
- Language(s) (NLP): Japanese
- License: MIT
- Finetuned from model [optional]: llm-jp-3-13b
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Direct Use
This model is designed for text generation tasks, especially those requiring efficient fine-tuning with limited GPU resources. The reduced sequence length (128 tokens) allows for better computational efficiency.
Downstream Use [optional]
Potential downstream tasks include:
・Text classification
・Sentiment analysis
・Named entity recognition
Out-of-Scope Use
This model is not intended for use in applications requiring long sequences exceeding 128 tokens, as it may truncate input data.
Bias, Risks, and Limitations
Biases
The model inherits biases from its base model and the fine-tuning dataset. Users should be cautious when applying it to sensitive or high-stakes tasks.
Risks
・Reduced sequence length may lead to loss of important context in longer inputs.
・Model predictions may reflect dataset biases.
Limitations
・Truncated max_seq_length=128 may impact performance on tasks requiring longer inputs.
・Fine-tuning was conducted with limited GPU resources, potentially affecting convergence.
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.
How to Get Started with the Model
Use the code below to get started with the model.
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "your-model-name-on-hf-hub"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
prompt = "あなたの質問やプロンプトをここに記載してください。"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Training Details
Training Data
The model was fine-tuned on a Japanese text dataset, based on the LoRA fine-tuning framework. Details of the dataset include:
・Source:
https://liat-aip.sakura.ne.jp/wp/llmのための日本語インストラクションデータ作成/llmのための日本語インストラクションデータ-公開/
関根聡, 安藤まや, 後藤美知子, 鈴木久美, 河原大輔, 井之上直也, 乾健太郎. ichikara-instruction: LLMのための日本語インストラクションデータの構築. 言語処理学会第30回年次大会(2024)
・Size: num rows = 1729
・Preprocessing: Tokenization using the base model tokenizer.
Training Procedure
Preprocessing: Tokenization with truncation at 128 tokens.
Framework: 🤗 Transformers + LoRA
Optimizer: AdamW
Learning Rate: 5e-5
Epochs: 1
Batch Size: 1
Regularization: lora_dropout
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime:
- Max Sequence Length: 128
- LoRA Rank: 16
- Dropout: 0.05
- Learning Rate: 5e-5
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the
Machine Learning Impact calculator presented in
Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
[More Information Needed]
Hardware
[More Information Needed]
Software
[More Information Needed]
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]
