miftahjaygemi199/llama3-rekomendasi-merged

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 29, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

miftahjaygemi199/llama3-rekomendasi-merged is an 8 billion parameter Llama 3 instruction-tuned model, finetuned by miftahjaygemi199. This model was optimized for faster training using Unsloth and Huggingface's TRL library. It is designed for general instruction-following tasks, leveraging the Llama 3 architecture for efficient performance.

Loading preview...

Model Overview

miftahjaygemi199/llama3-rekomendasi-merged is an 8 billion parameter Llama 3 instruction-tuned model, developed by miftahjaygemi199. It was finetuned from unsloth/llama-3-8b-Instruct-bnb-4bit and utilizes the Unsloth library for accelerated training, achieving a 2x speed improvement, in conjunction with Huggingface's TRL library.

Key Characteristics

  • Base Model: Llama 3 8B Instruct
  • Developer: miftahjaygemi199
  • Training Optimization: Leverages Unsloth for 2x faster finetuning.
  • License: Apache-2.0

Intended Use Cases

This model is suitable for a variety of instruction-following tasks, benefiting from the Llama 3 architecture's capabilities. Its optimized training process suggests a focus on efficient deployment and fine-tuning for specific applications.

Finetunes
2 models