| 586 |
Uncensor any LLM with abliteration |
2024-06-13 |
| 240 |
Microsoft Phi-2 model changes licence to MIT |
2024-01-06 |
| 197 |
Space secrets leak disclosure |
2024-06-01 |
| 181 |
Best 7B LLM on leaderboards made by an amateur following a medium tutorial |
2024-01-05 |
| 168 |
Llama 3 8B is almost as good as Wizard 2 8x22B |
2024-04-19 |
| 167 |
Nvidia releases NVLM 1.0 72B open weight model |
2024-10-02 |
| 163 |
Explaining the SDXL Latent Space |
2024-02-05 |
| 152 |
Hugging Face and Google partner for AI collaboration |
2024-01-25 |
| 131 |
A CC-By Open-Source TTS Model with Voice Cloning |
2024-11-04 |
| 127 |
FineWeb: Decanting the web for the finest text data at scale |
2024-06-02 |
| 103 |
HuggingChat: Chat with Open Source Models |
2024-02-21 |
| 425 |
Llama-3.3-70B-Instruct |
2024-12-06 |
| 348 |
A Replacement for BERT |
2024-12-19 |
| 394 |
Open-R1: an open reproduction of DeepSeek-R1 |
2025-01-28 |
| 227 |
Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser |
2025-02-07 |
| 451 |
Deepseek R1-0528 |
2025-05-28 |
| 149 |
Show HN: Penny-1.7B Irish Penny Journal style transfer |
2025-06-02 |
| 361 |
Nanonets-OCR-s – OCR model that transforms documents into structured markdown |
2025-06-16 |
| 388 |
Smollm3: Smol, multilingual, long-context reasoner LLM |
2025-07-08 |
| 152 |
Qwen3-235B-A22B-Thinking-2507 |
2025-07-25 |
| 166 |
Qwen3-4B-Thinking-2507 |
2025-08-06 |
| 319 |
Apertus 70B: Truly Open - Swiss LLM by ETH, EPFL and CSCS |
2025-09-02 |
| 262 |
The Smol Training Playbook: The Secrets to Building World-Class LLMs |
2025-10-30 |
| 978 |
DeepSeek-v3.2: Pushing the frontier of open large language models [pdf] |
2025-12-01 |
| 263 |
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning |
2025-12-01 |