Description

Lora entrenado con datasets en español por medio de un collab de unslothai con la idea de afinar un poco más el español que puede manejar el modelo Llama 3.2 3B.

Modo de uso

llama-server.exe -m Llama-3.2-1B-Instruct-abliterated.Q4_K_M.gguf --lora llama3.2_LoRA_Spanish.gguf

Uploaded model

  • Developed by: hwpoison89
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3.2-3b-instruct-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
8
GGUF
Model size
24.3M params
Architecture
llama
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model’s pipeline type.

Datasets used to train hwpoison89/Llama3.2_3B_LoRA_Spanish