Llama2.c: Inference llama 2 in one file of pure C (github.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of github.com: Llama2.c: Inference llama 2 in one file of pure C

First screen, captured 3 years ago.

Looks similar

Screenshot of github.com: Llm.c – LLM training in simple, pure C/CUDA

Llm.c – LLM training in simple, pure C/CUDA (github.com)

810 points by tosh 2 years ago | 134 comments

GitHub repository for llm.c, Andrej Karpathy's project for training LLMs like GPT-2 in simple, raw C/CUDA.

llm gpt-2 c cuda

Screenshot of github.com: 70B Llama 2 at 35tokens/second on 4090

70B Llama 2 at 35tokens/second on 4090 (github.com)

288 points by Palmik 3 years ago | 108 comments

Screenshot of github.com: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning

Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning (github.com)

216 points by KhoomeiK 2 years ago | 25 comments

Screenshot of github.com: Fiwix: Unix-like kernel for the i386 architecture

Fiwix: Unix-like kernel for the i386 architecture (github.com)

100 points by ingve 2 years ago | 30 comments

Screenshot of github.com: Peredvizhnikov Engine: Lock-free game engine written in C++20

Peredvizhnikov Engine: Lock-free game engine written in C++20 (github.com)

343 points by gjvc 3 years ago | 154 comments

GitHub repository for Peredvizhnikov Engine, a fully lock-free game engine written in C++20 and licensed under GPL-3.0.

cpp20 lock-free game-engine concurrency

Screenshot of docs.likejazz.com: Llama 3 implemented in pure NumPy

Llama 3 implemented in pure NumPy (docs.likejazz.com)

404 points by orixilus 2 years ago | 48 comments

GitHub repository llama3.np, a pure NumPy implementation of the Llama 3 language model for inference.

llama-3 numpy python llm

Related stories

Screenshot of github.com: Llamafile lets you distribute and run LLMs with a single file

Llamafile lets you distribute and run LLMs with a single file (github.com)

972 points by tfinch 2 years ago | 253 comments

GitHub repository for Mozilla-Ocho's llamafile, a tool to distribute and run large language models as a single executable file.

llamafile llama-cpp llm mozilla

Screenshot of github.com: Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders (github.com)

542 points by PaulPauls 1 year ago | 80 comments

GitHub repository with an end-to-end PyTorch pipeline for LLM interpretability using sparse autoencoders on Llama 3.2, replicating Anthropic/OpenAI/DeepMind research.

sparse-autoencoders mechanistic-interpretability llama-3 pytorch

Screenshot of docs.likejazz.com: Llama 3 implemented in pure NumPy

Llama 3 implemented in pure NumPy (docs.likejazz.com)

404 points by orixilus 2 years ago | 48 comments

GitHub repository llama3.np, a pure NumPy implementation of the Llama 3 language model for inference.

llama-3 numpy python llm

Screenshot of github.com: Llama.cpp 30B runs with only 6GB of RAM now

Llama.cpp 30B runs with only 6GB of RAM now (github.com)

1182 points by msoad 3 years ago | 356 comments

GitHub pull request #613 in llama.cpp by jart, merged, which uses mmap to make loading model weights 10-100x faster and reduce RAM usage.

llama-cpp llama mmap llm-inference

Screenshot of github.com: OpenLLaMA: An Open Reproduction of LLaMA

OpenLLaMA: An Open Reproduction of LLaMA (github.com)

414 points by sadiq 3 years ago | 144 comments

GitHub repository for OpenLLaMA, an Apache-2.0 licensed open reproduction of Meta's LLaMA language model, with a 200B-token preview release.

llama openllama large-language-models open-source-models

Screenshot of github.com: BitNet: Inference framework for 1-bit LLMs

BitNet: Inference framework for 1-bit LLMs (github.com)

357 points by redm 7 months ago | 163 comments

GitHub repository for Microsoft's BitNet, the official inference framework for 1-bit large language models.

bitnet 1-bit-llm quantization llm-inference