MoFHeka/LLaMA-Megatron
A LLaMA1/LLaMA12 Megatron implement.
This project helps machine learning engineers and researchers implement and run large language models (LLaMA) more efficiently. It takes LLaMA model checkpoints and tokenizer files as input, and outputs a configured LLaMA model ready for inference or further pretraining using the Megatron-LM framework. This is primarily for those working with large-scale natural language processing models.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking to run or pretrain LLaMA models with the performance and scalability benefits of Nvidia's Megatron-LM.
Not ideal if you are a non-technical user or do not have experience with large-scale deep learning frameworks and Python development environments.
Stars
28
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 13, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/MoFHeka/LLaMA-Megatron"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hkproj/pytorch-llama
LLaMA 2 implemented from scratch in PyTorch
4AI/LS-LLaMA
A Simple but Powerful SOTA NER Model | Official Code For Label Supervised LLaMA Finetuning
luchangli03/export_llama_to_onnx
export llama to onnx
ayaka14732/llama-2-jax
JAX implementation of the Llama 2 model
harleyszhang/lite_llama
A light llama-like llm inference framework based on the triton kernel.