Search: github.com/l4l | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

151.

Llama.cpp: Port of Facebook's LLaMA model in C/C++, with Apple Silicon support

github.com/ggerganov

3 years ago

989 points

152.

Facebook LLAMA is being openly distributed via torrents

github.com/facebookresearch

3 years ago

909 points

153.

Implementing a ChatGPT-like LLM from scratch, step by step

github.com/rasbt

2 years ago

739 points

154.

Llama.cpp: Full CUDA GPU Acceleration

github.com/ggerganov

3 years ago

728 points

155.

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

github.com/karpathy

3 years ago

707 points

156.

Show HN: I've built a locally running Perplexity clone

github.com/nilsherzig

2 years ago

669 points

157.

Reproducing GPT-2 in llm.c

github.com/karpathy

2 years ago

618 points

158.

Show HN: Llama 3.2 Interpretability with Sparse Autoencoders

github.com/PaulPauls

2 years ago

579 points

159.

Llama: Add grammar-based sampling

github.com/ggerganov

3 years ago

417 points

160.

Gemma 3 270M re-implemented in pure PyTorch for local tinkering

github.com/rasbt

10 months ago

417 points

161.

LLM4Decompile: Decompiling Binary Code with LLM

github.com/albertan017

2 years ago

412 points

162.

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy

github.com/ggerganov

2 years ago

382 points

163.

Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model

github.com/shawwn

3 years ago

343 points

164.

LLama.cpp now has a web interface

github.com/ggerganov

3 years ago

328 points

165.

NotebookLlama: An open source version of NotebookLM

github.com/meta-llama

2 years ago

322 points

166.

Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2

github.com/trholding

3 years ago

320 points

167.

Llama 3.1 Omni Model

github.com/ictnlp

2 years ago

304 points

168.

Right-sizes LLM models to your system's RAM, CPU, and GPU

github.com/AlexsJones

4 months ago

301 points

169.

M2 Ultra can run 128 streams of Llama 2 7B in parallel

github.com/ggerganov

3 years ago

268 points

170.

LLVM merges SafeStack

github.com/llvm-mirror

11 years ago

267 points

171.

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training

github.com/alainnothere

3 months ago

265 points

172.

Show HN: S3mini – Tiny and fast S3-compatible client, no-deps, edge-ready

github.com/good-lly

a year ago

261 points

173.

Fork of Facebook’s LLaMa model to run on CPU

github.com/markasoftware

3 years ago

246 points

174.

MIT's Scratch Team releases Scratch 2.0 editor and player as open source

12 years ago

239 points

175.

Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning

github.com/KhoomeiK

2 years ago

239 points

176.

Show HN: ChatGPT Plugins are a security nightmare

github.com/greshake

3 years ago

238 points

177.

Show HN: Lldap, a Simplified LDAP Server

github.com/nitnelave

4 years ago

229 points

178.

Languages on BEAM, the Erlang virtual machine

github.com/llaisdy

9 years ago

225 points

179.

Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2

github.com/getumbrel

3 years ago

225 points

180.

Llama-Scan: Convert PDFs to Text W Local LLMs

github.com/ngafar

10 months ago

221 points