YongdongWang/llama-3.2-1b-lora-qlora-dart-llm-gguf

This repository contains GGUF quantized versions of the Llama 3.2 1B DART LLM model, fine-tuned for robot task planning in construction environments. — Base Model: meta-llama/Llama-3.2-1B — Fine-tuned Version: Based on QLoRA fine-tuned model for robotics task planning — Format: GGUF (GPT-Generated Unified Format) — Use Case: Optimized for inference with llama.cpp and compatible frameworks — q5km: llama3.21b-lora-qlora-dart-llmq5km.gguf` — 5-bit mixed quantization Different quantization levels offer trade-offs between model size, inference speed, and quality: — f16: Full 16-bit precision (largest, highest quality) — q80: 8-

Модальности:
Генерация текста

Задача: Генерация текста
Автор: YongdongWang
Теги: gguf, llama, quantized, robotics, task-planning, construction, dart-llm, en
Лайков: 3  |  Загрузок: 42

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.