26 lines
1.2 KiB
Markdown
26 lines
1.2 KiB
Markdown
---
|
|
license: llama3
|
|
tags:
|
|
- unsloth
|
|
datasets:
|
|
- Danda245/medical-qa-id-llama-split
|
|
language:
|
|
- id
|
|
base_model:
|
|
- GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct
|
|
pipeline_tag: 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](https://huggingface.co/aisingapore/llama3-8b-cpt-sea-lionv2-base)
|
|
- **Fine-Tuned Version:** [GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct](https://huggingface.co/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](https://huggingface.co/datasets/Danda245/medical-qa-id-llama-split)
|