Top Hackernews posts from huggingface.co

1. Uncensor any LLM with abliteration (huggingface.co)
   586 points by mizzao over 2 years | 287 comments
2. Try Stable Diffusion's Img2Img Mode (huggingface.co)
   415 points by fragmede about 4 years | 156 comments
3. MonadGPT – What would have happened if ChatGPT was invented in the 17th century? (huggingface.co)
   323 points by surprisetalk almost 3 years | 116 comments
4. LLM in a Flash: Efficient LLM Inference with Limited Memory (huggingface.co)
   252 points by ghshephard over 2 years | 53 comments
5. Microsoft Phi-2 model changes licence to MIT (huggingface.co)
   240 points by regularfry over 2 years | 90 comments
6. Falcon 180B (huggingface.co)
   238 points by osanseviero about 3 years | 208 comments
7. OpenLLaMA 13B Released (huggingface.co)
   229 points by tosh about 3 years | 107 comments
8. T0* – Series of encoder-decoder models trained on a large set of different tasks (huggingface.co)
   218 points by julien_c almost 5 years | 153 comments
9. Hugging Face Releases Agents (huggingface.co)
   214 points by mach1ne over 3 years | 125 comments
10. PaddleOCR: Lightweight, 80 Langauge OCR (huggingface.co)
    200 points by zuhayeer about 5 years | 58 comments
11. Space secrets leak disclosure (huggingface.co)
    197 points by markyg over 2 years | 83 comments
12. BigCode Project Releases StarCoder: A 15B Code LLM (huggingface.co)
    185 points by enum over 3 years | 37 comments
13. Best 7B LLM on leaderboards made by an amateur following a medium tutorial (huggingface.co)
    181 points by Der_Einzige over 2 years | 49 comments
14. AnimeGANv2: Convert Face Portraits into Anime (huggingface.co)
    180 points by aliabd almost 5 years | 65 comments
15. Stability.ai sent a take down request to Runway ML's SD v1.5 citing IP Leak (huggingface.co)
    179 points by amrrs almost 4 years | 72 comments
16. We raised $100M for open and collaborative machine learning (huggingface.co)
    175 points by minimaxir over 4 years | 47 comments
17. SantaCoder: A new 1.1B code model for generation and infilling (huggingface.co)
    168 points by moyix over 3 years | 74 comments
18. Llama 3 8B is almost as good as Wizard 2 8x22B (huggingface.co)
    168 points by tosh over 2 years | 111 comments
19. StackLlama: A hands-on guide to train LlaMa with RLHF (huggingface.co)
    165 points by kashifr over 3 years | 38 comments
20. Explaining the SDXL Latent Space (huggingface.co)
    163 points by thesephist over 2 years | 33 comments
21. Hugging Face and Google partner for AI collaboration (huggingface.co)
    152 points by powera over 2 years | 57 comments
22. Wordalle – Guess the prompt used to generate a set of images from DalleMini (huggingface.co)
    137 points by itaygabb about 4 years | 15 comments
23. Mistral-8x7B-Chat (huggingface.co)
    131 points by birriel almost 3 years | 69 comments
24. FineWeb: Decanting the web for the finest text data at scale (huggingface.co)
    127 points by nmstoker over 2 years | 14 comments
25. The age of machine learning as code has arrived (huggingface.co)
    117 points by gk1 almost 5 years | 54 comments
26. Yi-34B-Chat (huggingface.co)
    115 points by tosh almost 3 years | 63 comments
27. GPT-3.5 and Wolfram Alpha via LangChain (huggingface.co)
    107 points by heliophobicdude over 3 years | 8 comments
28. The Falcon has landed in the Hugging Face ecosystem (huggingface.co)
    105 points by minimaxir over 3 years | 40 comments
29. HuggingChat: Chat with Open Source Models (huggingface.co)
    103 points by victormustar over 2 years | 42 comments
30. Hugging Face and AWS partner to make AI more accessible (huggingface.co)
    102 points by rjtavares over 3 years | 41 comments
31. HuggingFace Training Cluster as a Service (huggingface.co)
    101 points by kashifr about 3 years | 45 comments
32. More than 80 AI models from Qualcomm (huggingface.co)
    95 points by Brajeshwar over 2 years | 47 comments
33. Segmind Stable Diffusion – A smaller version of Stable Diffusion XL (huggingface.co)
    95 points by sayak_hf almost 3 years | 39 comments
34. LLaMA-Pro-8B (huggingface.co)
    94 points by tosh over 2 years | 29 comments
35. HuggingChat (huggingface.co)
    93 points by kalendos over 3 years | 17 comments
36. Yarn-Mistral-7B-128k (huggingface.co)
    88 points by tosh almost 3 years | 18 comments
37. Apple/OpenELM: Efficient Open-Source Family Language Models (huggingface.co)
    82 points by panqueca over 2 years | 13 comments
38. Sparse LLM Inference on CPU: 75% fewer parameters (huggingface.co)
    78 points by freediver almost 3 years | 2 comments
39. Pokemon GAN (huggingface.co)
    77 points by aliabd over 4 years | 30 comments
40. YouTube-Commons: Audio transcripts of 2,063,066 YouTube videos, CC-By license (huggingface.co)
    75 points by CharlesW over 2 years | 9 comments
41. Switch Transformers C – 2048 experts (1.6T params for 3.1 TB) (2022) (huggingface.co)
    73 points by tosh almost 3 years | 36 comments
42. Few-Shot Learning in Practice: GPT-Neo & 'HuggingFace' Accelerated Inference API (huggingface.co)
    69 points by homarp over 5 years | 3 comments
43. Show HN: Simply Reading Analog Gauges – GPT4, CogVLM Can't (huggingface.co)
    66 points by icecoffee over 2 years | 41 comments
44. Multimodal Neurons in Pretrained Text-Only Transformers (huggingface.co)
    66 points by famouswaffles about 3 years | 53 comments
45. HuggingChat – ChatGPT alternative with open source models (huggingface.co)
    61 points by victormustar almost 3 years | 6 comments
46. Find images from movies based on what you draw (huggingface.co)
    61 points by zuhayeer almost 5 years | 30 comments
47. OpenLLaMA 7B Training Completed to 1T Tokens (huggingface.co)
    58 points by jncraton over 3 years | 3 comments
48. MSFT's WizardLM2 models have been taken down (huggingface.co)
    58 points by null_point over 2 years | 25 comments
49. Phi-2 (huggingface.co)
    57 points by tosh almost 3 years | 5 comments
50. Dolphin-2_6-Phi-2 (huggingface.co)
    56 points by tosh over 2 years | 22 comments
51. Alibaba releases 72B LLM with 32k context length (huggingface.co)
    55 points by logicchains almost 3 years | 84 comments
52. LiteLlama-460M-1T has 460M parameters trained with 1T tokens (huggingface.co)
    54 points by dmezzetti over 2 years | 28 comments
53. Large Language Models: A New Moore's Law? (huggingface.co)
    54 points by EvgeniyZh almost 5 years | 22 comments
54. LLaMA 3 70B Llamafiles (huggingface.co)
    51 points by birriel over 2 years | 22 comments