TencentARC/LLaMA-Pro
[ACL 2024] Progressive LLaMA with Block Expansion.
This project offers an advanced large language model (LLM) designed to excel in complex reasoning tasks, particularly in mathematics and coding. It takes general text prompts or specific math problems as input and generates highly accurate solutions or detailed code. This tool is ideal for AI researchers and developers who are building or evaluating sophisticated language models and need state-of-the-art performance in logical and mathematical domains.
514 stars. No commits in the last 6 months.
Use this if you are a researcher or developer focused on building or fine-tuning advanced language models and need superior performance in mathematical reasoning and code generation.
Not ideal if you are looking for a general-purpose conversational AI or a tool for simple text generation tasks without a strong emphasis on complex logical deduction.
Stars
514
Forks
40
Language
Python
License
Apache-2.0
Category
Last pushed
May 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/TencentARC/LLaMA-Pro"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ModelCloud/GPTQModel
LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD...
intel/auto-round
🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality...
pytorch/ao
PyTorch native quantization and sparsity for training and inference
bodaay/HuggingFaceModelDownloader
Simple go utility to download HuggingFace Models and Datasets
NVIDIA/kvpress
LLM KV cache compression made easy