Model Card for Model ID

結果

手順/procedure

• ja

1. meta-llama/Meta-Llama-3-8B-Instructとlightblue/suzume-llama-3-8B-japaneseの差分を作成
2. shapeが異なるので、差分をmeta-llama/Meta-Llama-3-70B-Instruct用にアップサンプリング
3. 前から 8-layer、最後から8-layerはそのまま適用
4. 中間layerを引き延ばして適用

• en

1. Create the difference between meta-llama/Meta-Llama-3-8B-Instruct and lightblue/zume-llama-3-8B-japanese
2. Since the shapes are different, the difference is upsampled for meta-llama/Meta-Llama-3-70B-Instruct
3. Apply the 8 layers from the front and 8 layers from the end as they are.
4. Continue applying the middle layer

Model Details

Model Description

• Developed by: [More Information Needed]
• 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

Downstream Use [optional]

Out-of-Scope Use

Bias, Risks, and Limitations

Recommendations

How to Get Started with the Model

Training Details

Training Data

Training Procedure

Preprocessing [optional]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

Evaluation

Testing Data, Factors & Metrics

Testing Data

Factors

Metrics

Results

Summary

Model Examination [optional]

Environmental Impact

• 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

Compute Infrastructure

Hardware

Software

Citation [optional]

Glossary [optional]

More Information [optional]

Model Card Authors [optional]

Model Card Contact