| 586 |
Uncensor any LLM with abliteration |
2024-06-13 |
| 415 |
Try Stable Diffusion's Img2Img Mode |
2022-08-29 |
| 323 |
MonadGPT – What would have happened if ChatGPT was invented in the 17th century? |
2023-11-24 |
| 252 |
LLM in a Flash: Efficient LLM Inference with Limited Memory |
2023-12-20 |
| 240 |
Microsoft Phi-2 model changes licence to MIT |
2024-01-06 |
| 238 |
Falcon 180B |
2023-09-06 |
| 229 |
OpenLLaMA 13B Released |
2023-06-18 |
| 218 |
T0* – Series of encoder-decoder models trained on a large set of different tasks |
2021-10-18 |
| 214 |
Hugging Face Releases Agents |
2023-05-10 |
| 200 |
PaddleOCR: Lightweight, 80 Langauge OCR |
2021-09-09 |
| 197 |
Space secrets leak disclosure |
2024-06-01 |
| 185 |
BigCode Project Releases StarCoder: A 15B Code LLM |
2023-05-04 |
| 181 |
Best 7B LLM on leaderboards made by an amateur following a medium tutorial |
2024-01-05 |
| 180 |
AnimeGANv2: Convert Face Portraits into Anime |
2021-11-09 |
| 179 |
Stability.ai sent a take down request to Runway ML's SD v1.5 citing IP Leak |
2022-10-20 |
| 175 |
We raised $100M for open and collaborative machine learning |
2022-05-09 |
| 168 |
Llama 3 8B is almost as good as Wizard 2 8x22B |
2024-04-19 |
| 168 |
SantaCoder: A new 1.1B code model for generation and infilling |
2022-12-22 |
| 167 |
Nvidia releases NVLM 1.0 72B open weight model |
2024-10-02 |
| 165 |
StackLlama: A hands-on guide to train LlaMa with RLHF |
2023-04-06 |
| 163 |
Explaining the SDXL Latent Space |
2024-02-05 |
| 160 |
BLOOM: The largest open multilingual language model |
2022-07-12 |
| 152 |
Hugging Face and Google partner for AI collaboration |
2024-01-25 |
| 137 |
Wordalle – Guess the prompt used to generate a set of images from DalleMini |
2022-07-01 |
| 131 |
Mistral-8x7B-Chat |
2023-12-10 |
| 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 |
| 117 |
The age of machine learning as code has arrived |
2021-10-22 |
| 115 |
Yi-34B-Chat |
2023-11-24 |
| 107 |
GPT-3.5 and Wolfram Alpha via LangChain |
2023-01-18 |
| 105 |
The Falcon has landed in the Hugging Face ecosystem |
2023-06-05 |
| 103 |
HuggingChat: Chat with Open Source Models |
2024-02-21 |
| 102 |
Hugging Face and AWS partner to make AI more accessible |
2023-02-21 |
| 101 |
HuggingFace Training Cluster as a Service |
2023-09-05 |
| 95 |
More than 80 AI models from Qualcomm |
2024-02-28 |
| 95 |
Segmind Stable Diffusion – A smaller version of Stable Diffusion XL |
2023-10-25 |
| 94 |
LLaMA-Pro-8B |
2024-01-06 |
| 93 |
HuggingChat |
2023-04-25 |
| 88 |
Yarn-Mistral-7B-128k |
2023-11-11 |
| 82 |
Apple/OpenELM: Efficient Open-Source Family Language Models |
2024-04-24 |
| 78 |
Sparse LLM Inference on CPU: 75% fewer parameters |
2023-10-19 |
| 77 |
Pokemon GAN |
2022-02-14 |
| 75 |
YouTube-Commons: Audio transcripts of 2,063,066 YouTube videos, CC-By license |
2024-04-18 |
| 73 |
Switch Transformers C – 2048 experts (1.6T params for 3.1 TB) (2022) |
2023-11-20 |
| 69 |
Few-Shot Learning in Practice: GPT-Neo & 'HuggingFace' Accelerated Inference API |
2021-06-04 |
| 66 |
Multimodal Neurons in Pretrained Text-Only Transformers |
2023-08-04 |
| 66 |
Show HN: Simply Reading Analog Gauges – GPT4, CogVLM Can't |
2024-01-22 |
| 61 |
Find images from movies based on what you draw |
2021-10-13 |
| 61 |
HuggingChat – ChatGPT alternative with open source models |
2023-12-15 |
| 58 |
MSFT's WizardLM2 models have been taken down |
2024-04-16 |
| 58 |
OpenLLaMA 7B Training Completed to 1T Tokens |
2023-06-07 |
| 57 |
Phi-2 |
2023-12-13 |
| 56 |
Dolphin-2_6-Phi-2 |
2023-12-24 |
| 55 |
Alibaba releases 72B LLM with 32k context length |
2023-11-30 |
| 54 |
LiteLlama-460M-1T has 460M parameters trained with 1T tokens |
2024-01-07 |
| 54 |
Large Language Models: A New Moore's Law? |
2021-10-27 |
| 52 |
Fine-Tuning LLMs to 1.58bit |
2024-09-18 |
| 51 |
LLaMA 3 70B Llamafiles |
2024-04-19 |
| 47 |
Improving Parquet Dedupe on Hugging Face Hub |
2024-10-08 |
| 47 |
Open LLAMA 13B released, trained on 1T tokens |
2023-06-19 |
| 46 |
DALL·E Mini |
2022-04-11 |
| 46 |
Open-LLM performances are plateauing |
2024-06-29 |
| 46 |
The AI Research Residency Program |
2022-03-23 |
| 45 |
Show HN: Interpretable Text Classification and Clustering in the Browser |
2021-12-20 |
| 41 |
4-Bit Quantization and QLoRA |
2023-05-25 |
| 40 |
BLOOMChat, a 176B parameter, Multi-lingual, fine tuned chat |
2023-05-19 |
| 40 |
What's Going on with the Open LLM Leaderboard? |
2023-06-23 |
| 39 |
Kai-Fu Li's Yi-34B uses exactly Llama's architecture except for 2 tensor renamed |
2023-11-14 |
| 37 |
Zephyr 7B – Mistral Finetune that responds like ChatGPT |
2023-10-15 |
| 36 |
Whisper Jax: Transcribe a 1 hour of audio in under 15 seconds |
2023-04-22 |
| 34 |
MistralLite by Amazon Web Services |
2023-11-01 |
| 33 |
Mixtral-8x22B on HuggingFace |
2024-04-10 |
| 31 |
General OCR Theory: Towards OCR-2.0 via a Unified End-to-End Model |
2024-09-11 |
| 30 |
Zephyr 141B, a Mixtral 8x22B fine-tune, is now available in Hugging Chat |
2024-04-12 |
| 30 |
OpenFLUX.1 |
2024-10-04 |
| 29 |
Mistral 7B v0.2 |
2024-03-31 |
| 29 |
Mixture of Experts Explained |
2023-12-11 |
| 29 |
TinyLlama at 2T of 3T |
2023-11-19 |
| 28 |
Video2Game: Real-Time, Interactive, Realistic Environment from a Single Video |
2024-04-16 |
| 27 |
Real-Time Latent Consistency Model |
2023-10-30 |
| 27 |
Language Modeling Is Compression |
2023-09-21 |
| 26 |
Llama-3.2-3B-Instruct-uncensored |
2024-09-27 |
| 26 |
Pixel Art XL: Stable Diffusion XL for Pixel Art |
2023-08-03 |
| 26 |
UC Berkeley's open-source Vicuna LLM chatbot released new improved model weights |
2023-04-14 |
| 26 |
Llama can now see and run on your device – welcome Llama 3.2 |
2024-09-25 |
| 25 |
Llama 1.3B Trained on 200B Tokens for Commercial Use |
2023-04-28 |
| 25 |
New Phi-3.5 Models from Microsoft, including new MoE |
2024-08-20 |
| 25 |
LLM: Transformer Is Linear |
2024-05-24 |
| 425 |
Llama-3.3-70B-Instruct |
2024-12-06 |
| 348 |
A Replacement for BERT |
2024-12-19 |
| 48 |
DeepSeek v3 beats Claude sonnet 3.5 and way cheaper |
2024-12-26 |
| 52 |
Train faster static embedding models with sentence transformers |
2025-01-15 |
| 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 |
| 49 |
Janus-Pro: Autoregressive framework unifying multimodal understanding&generation |
2025-01-27 |
| 39 |
DeepSeek-R1-Distill-Qwen-1.5B Surpasses GPT-4o in certain benchmarks |
2025-01-20 |
| 38 |
Fully autonomous AI agents should not be developed |
2025-02-07 |
| 33 |
The Ultra-Scale Playbook: Training LLMs on GPU Clusters |
2025-02-19 |