license, tags, datasets, language, base_model, pipeline_tag
| license | tags | datasets | language | base_model | pipeline_tag | ||||
|---|---|---|---|---|---|---|---|---|---|
| llama3 |
|
|
|
|
text-generation |
SkylarWhite/llama3-8b-cpt-sahabatai-v1-instruct
This model is a fine-tuned version of the aisingapore/llama3-8b-cpt-sea-lionv2-base, optimized for instruction-based tasks in the Indonesian language. It is specifically designed for providing structured responses and expert-like advice.
Model Sources
- Original Base Model: aisingapore/llama3-8b-cpt-sea-lionv2-base
- Fine-Tuned Version: GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
- GGUF Conversion: Supports 4-bit, 5-bit, 8-bit, and 16-bit quantized formats.
Dataset
The model was fine-tuned using the Danda245/medical-qa-id-llama-split dataset, which contains Indonesian medical question-answer pairs. The dataset includes:
- Dataset Repository: Danda245/medical-qa-id-llama-split