Search: huggingface.co | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

241.

Open-R1: an open reproduction of DeepSeek-R1

a year ago

394 points

242.

Smollm3: Smol, multilingual, long-context reasoner LLM

a year ago

388 points

243.

5 months ago

378 points

244.

Nanonets-OCR-s – OCR model that transforms documents into structured markdown

a year ago

361 points

245.

A Replacement for BERT

2 years ago

348 points

246.

MonadGPT – What would have happened if ChatGPT was invented in the 17th century?

3 years ago

323 points

247.

Apertus 70B: Truly Open - Swiss LLM by ETH, EPFL and CSCS

10 months ago

323 points

248.

The Smol Training Playbook: The Secrets to Building World-Class LLMs

8 months ago

265 points

249.

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

7 months ago

264 points

250.

LLM in a Flash: Efficient LLM Inference with Limited Memory

3 years ago

252 points

251.

Microsoft Phi-2 model changes licence to MIT

2 years ago

240 points

252.

3 years ago

238 points

253.

OpenLLaMA 13B Released

3 years ago

229 points

254.

Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser

a year ago

227 points

255.

T0* – Series of encoder-decoder models trained on a large set of different tasks

5 years ago

218 points

256.

Hugging Face Releases Agents

3 years ago

214 points

257.

A neural network to auto-complete your thoughts

transformer.huggingface.co

7 years ago

211 points

258.

PaddleOCR: Lightweight, 80 Langauge OCR

5 years ago

200 points

259.

Qwen3-4B-Thinking-2507

a year ago

198 points

260.

Space secrets leak disclosure

2 years ago

197 points

261.

BigCode Project Releases StarCoder: A 15B Code LLM

3 years ago

185 points

262.

Best 7B LLM on leaderboards made by an amateur following a medium tutorial

2 years ago

181 points

263.

AnimeGANv2: Convert Face Portraits into Anime

5 years ago

180 points

264.

Stability.ai sent a take down request to Runway ML's SD v1.5 citing IP Leak

4 years ago

179 points

265.

We raised $100M for open and collaborative machine learning

4 years ago

175 points

266.

Llama 3 8B is almost as good as Wizard 2 8x22B

2 years ago

168 points

267.

SantaCoder: A new 1.1B code model for generation and infilling

4 years ago

168 points

268.

Nvidia releases NVLM 1.0 72B open weight model

2 years ago

167 points

269.

StackLlama: A hands-on guide to train LlaMa with RLHF

3 years ago

165 points

270.

Explaining the SDXL Latent Space

2 years ago

163 points