Search: github.com/llvm | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

481.

Show HN: LLM Token Visualizer (tokenvisualizer.netlify.app)

1 point

3 years ago

482.

Show HN: LLM OSINT, letting GPT-4 Google about you (github.com/sshh12)

1 point

3 years ago

483.

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

1311 points

3 years ago

484.

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

1050 points

2 years ago

485.

Llama3 implemented from scratch (github.com/naklecha)

1041 points

2 years ago

486.

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

989 points

3 years ago

487.

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

909 points

3 years ago

488.

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

739 points

2 years ago

489.

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

728 points

3 years ago

490.

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

707 points

3 years ago

491.

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

618 points

2 years ago

492.

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

579 points

2 years ago

493.

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

417 points

3 years ago

494.

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

417 points

10 months ago

495.

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

412 points

2 years ago

496.

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

382 points

2 years ago

497.

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

343 points

3 years ago

498.

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

328 points

3 years ago

499.

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

322 points

2 years ago

500.

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

320 points

3 years ago

501.

Llama 3.1 Omni Model (github.com/ictnlp)

304 points

2 years ago

502.

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

301 points

3 months ago

503.

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

268 points

3 years ago

504.

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

265 points

3 months ago

505.

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

246 points

3 years ago

506.

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

239 points

2 years ago

507.

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

238 points

3 years ago

508.

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

225 points

3 years ago

509.

Llama-Scan: Convert PDFs to Text W Local LLMs (github.com/ngafar)

221 points

10 months ago

510.

llama-fs: A self-organizing file system with llama 3 (github.com/iyaja)

221 points

2 years ago