Search: github.com/lkl | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

151.

Llama3 implemented from scratch (github.com/naklecha)

1041 points

2 years ago

152.

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

989 points

3 years ago

153.

Facebook LLAMA is being openly distributed via torrents (github.com/facebookresearch)

909 points

3 years ago

154.

Implementing a ChatGPT-like LLM from scratch, step by step (github.com/rasbt)

739 points

2 years ago

155.

Llama.cpp: Full CUDA GPU Acceleration (github.com/ggerganov)

728 points

3 years ago

156.

Llama2.c: Inference llama 2 in one file of pure C (github.com/karpathy)

707 points

3 years ago

157.

Show HN: I've built a locally running Perplexity clone (github.com/nilsherzig)

669 points

2 years ago

158.

Reproducing GPT-2 in llm.c (github.com/karpathy)

618 points

2 years ago

159.

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

579 points

2 years ago

160.

Llama: Add grammar-based sampling (github.com/ggerganov)

417 points

3 years ago

161.

Gemma 3 270M re-implemented in pure PyTorch for local tinkering (github.com/rasbt)

417 points

10 months ago

162.

LLM4Decompile: Decompiling Binary Code with LLM (github.com/albertan017)

412 points

2 years ago

163.

New exponent functions that make SiLU and SoftMax 2x faster, at full accuracy (github.com/ggerganov)

382 points

2 years ago

164.

Show HN: Llama-dl – high-speed download of LLaMA, Facebook's 65B GPT model (github.com/shawwn)

343 points

3 years ago

165.

LLama.cpp now has a web interface (github.com/ggerganov)

328 points

3 years ago

166.

NotebookLlama: An open source version of NotebookLM (github.com/meta-llama)

322 points

2 years ago

167.

Llama 2 Everywhere (L2E): Standalone, Binary Portable, Bootable Llama 2 (github.com/trholding)

320 points

3 years ago

168.

Llama 3.1 Omni Model (github.com/ictnlp)

304 points

2 years ago

169.

Right-sizes LLM models to your system's RAM, CPU, and GPU (github.com/AlexsJones)

301 points

3 months ago

170.

M2 Ultra can run 128 streams of Llama 2 7B in parallel (github.com/ggerganov)

268 points

3 years ago

171.

LLVM merges SafeStack (github.com/llvm-mirror)

267 points

11 years ago

172.

Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training (github.com/alainnothere)

265 points

3 months ago

173.

Show HN: S3mini – Tiny and fast S3-compatible client, no-deps, edge-ready (github.com/good-lly)

261 points

a year ago

174.

Fork of Facebook’s LLaMa model to run on CPU (github.com/markasoftware)

246 points

3 years ago

175.

MIT's Scratch Team releases Scratch 2.0 editor and player as open source (github.com/LLK)

239 points

12 years ago

176.

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

239 points

2 years ago

177.

Show HN: ChatGPT Plugins are a security nightmare (github.com/greshake)

238 points

3 years ago

178.

Show HN: Lldap, a Simplified LDAP Server (github.com/nitnelave)

229 points

4 years ago

179.

Languages on BEAM, the Erlang virtual machine (github.com/llaisdy)

225 points

9 years ago

180.

Show HN: LlamaGPT – Self-hosted, offline, private AI chatbot, powered by Llama 2 (github.com/getumbrel)

225 points

3 years ago