SipanGPT-0.2-Llama-3.2-1B-GGUF/README.md

base_model, language, license, tags, datasets, pipeline_tag, new_version

base_model	language	license	tags	datasets	pipeline_tag	new_version
unsloth/Meta-Llama-3.2-1B-Instruct	es	apache-2.0	text-generation-inference transformers unsloth llama gguf q4_k_m 4bit sharegpt pretaining finetuning Q5_K_M Q8_0 uss Perú Lambayeque Chiclayo	ussipan/sipangpt	text2text-generation	ussipan/SipanGPT-0.3-Llama-3.2-1B-GGUF

SipánGPT 0.2 Llama 3.2 1B GGUF

• Modelo pre-entrenado para responder preguntas de la Universidad Señor de Sipán de Lambayeque, Perú.
• Pre-trained model to answer questions from the Señor de Sipán University of Lambayeque, Peru.

Testing the model

• Debido a la cantidad de conversaciones con las que fue entrenado (5400 conversaciones), el modelo genera bastantes alucinaciones.
• Due to the number of conversations with which it was trained (5400 conversations), the model generates quite a few hallucinations.

Uploaded model

• Developed by: jhangmez
• License: apache-2.0
• Finetuned from model : unsloth/Meta-Llama-3.2-1B-Instruct

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

---

SipánGPT 0.2 Llama 3.2 1B GGUF

Hecho con ❤️ por Jhan Gómez P.