I will fine tune llm models with lora and evaluation

Parte de la información aparece en idioma inglés.

Estados Unidos

Hablo Inglés

LLM Fine Tuning and Evaluation

I specialize in fine tuning and shaping language models for real world use. My work focuses on LoRA/QLoRA training, frontier model distillation, and structured evaluation turning general models into ...
Acerca de este Servicio

 I fine tune and optimize LLMs using LoRA/QLoRA and structured evaluation to improve real world performance.


This includes dataset guidance, A/B testing, and benchmark reporting to ensure measurable improvements not guesswork.


I focus on building reliable, domain specific systems for business and technical use cases.

No NSFW. No image LoRAs.


Please message before ordering to ensure the best fit.

Lenguaje de programación:

Python

Pytorch

TensorFlow

Marcos y herramientas de modelos de IA:

TensorFlow

PyTorch

Tipo de datos:

Texto

Datos tabulares

Multimodal

Motor de IA:

GPT

Gemini

TensorFlow

Llama

PyTorch

Otros