Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Kimina-Prover: Applying Test-Time RL Search on Large Formal Reasoning Models (huggingface.co)
1 point by ibobev 12 days ago | past | discuss
We Got Claude to Fine-Tune an Open Source LLM (huggingface.co)
1 point by ibobev 12 days ago | past | discuss
DeepFabric. Train and Evaluate Model Behavior with Structured Data (huggingface.co)
1 point by decodebytes 12 days ago | past | discuss
Microsoft open sources text-to-speech model VibeVoice‑Realtime‑0.5B (huggingface.co)
5 points by yakkomajuri 12 days ago | past | discuss
The LLM Evaluation Guidebook (huggingface.co)
3 points by aratahikaru5 13 days ago | past | discuss
HunyuanOCR by Tencent: A 1B Parameter End to End OCR Expert VLM (huggingface.co)
15 points by maxloh 13 days ago | past | discuss
Ellora: Enhancing LLMs with LoRA Standardized Recipes for Capability Enhancement (huggingface.co)
1 point by codelion 14 days ago | past
Mistral misspelled Ministral on HuggingFace and Ollama (huggingface.co)
4 points by mrtimo 14 days ago | past | 1 comment
Transformers v5.0 by HuggingFace (huggingface.co)
2 points by satvikpendem 15 days ago | past
Eiffel Llama: Open-Source Replication of Claude's Golden Gate Experiment (huggingface.co)
1 point by victormustar 15 days ago | past
Transformers v5 Is Out (huggingface.co)
7 points by unofficialmerve 15 days ago | past | 1 comment
Apple: STARFlow-V, a Normalizing Flow Model for Causal Video Generation (huggingface.co)
4 points by eyk19 15 days ago | past
DeepSeek-v3.2: Pushing the frontier of open large language models [pdf] (huggingface.co)
982 points by pretext 15 days ago | past | 465 comments
DeepSeek-v3.2 and v3.2 Speciale Announced (huggingface.co)
5 points by diwank 15 days ago | past
DeepSeek-v3.2-Speciale (huggingface.co)
20 points by b16m 15 days ago | past
DeepSeek-v3.2 (huggingface.co)
63 points by meetpateltech 15 days ago | past | 1 comment
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning (huggingface.co)
264 points by victorbuilds 16 days ago | past | 88 comments
Porting nanochat to Transformers: an AI modeling history lesson (huggingface.co)
1 point by victormustar 16 days ago | past
Z-Image Generation Demo (huggingface.co)
1 point by doener 16 days ago | past
In-Depth Analysis of the Latest Deep Research Technology (huggingface.co)
1 point by tamnd 17 days ago | past
Show HN: Dante-Qwen-4B – Curing LLM "Neurosis" with a Divine Comedy Curriculum (huggingface.co)
5 points by hunterbown 18 days ago | past | 1 comment
SAM3D-Body with glb export in rerun (huggingface.co)
3 points by pablovelagomez 18 days ago | past | 1 comment
DeepSeek-AI/DeepSeek-Math-V2 (huggingface.co)
8 points by vismit2000 19 days ago | past
Built an AI agent that creates block code (huggingface.co)
1 point by owenkaplinsky 19 days ago | past | 1 comment
Porting Nanochat to Transformers (huggingface.co)
2 points by us321 19 days ago | past
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning (huggingface.co)
18 points by nekofneko 19 days ago | past
Z-Image Turbo Released – 6B Parameter Text to Image Model (huggingface.co)
8 points by rossriley 20 days ago | past | 1 comment
The Eiffel Tower Llama (huggingface.co)
2 points by aaraujo002 20 days ago | past
Continuous Batching (huggingface.co)
3 points by homarp 20 days ago | past
Diffusers Welcomes Flux-2 (huggingface.co)
1 point by ibobev 21 days ago | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: