Hugging Face's logo
William Suffill's picture
1 7 48

William Suffill

wsuff
shtefcs's profile picture
Ā·

AI & ML interests

None yet

Recent Activity

reacted to nicolay-r's post with šŸ‘ 26 days ago
šŸ“¢ For those who wish to launch distilled DeepSeek R1 for reasoning with schema, sharing the Google Colab notebook: šŸ“™ https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_deep_seek_7b_distill_colab.ipynb This is a wrapper of the Qwen2 transformers šŸ¤— provider via bulk-chain framework. Model: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B GPU: T4 (15GB) is nearly enough in float32 mode. šŸš€ To boost the performance you may set bf16 mode (use_bf16=True) šŸŒŸ Powered by bulk-chain: https://github.com/nicolay-r/bulk-chain
reacted to m-ric's post with šŸ”„ 27 days ago
š—§š—µš—² š—›š˜‚š—Æ š˜„š—²š—¹š—°š—¼š—ŗš—²š˜€ š—²š˜…š˜š—²š—暝—»š—®š—¹ š—¶š—»š—³š—²š—暝—²š—»š—°š—² š—½š—暝—¼š˜ƒš—¶š—±š—²š—暝˜€! āœ… Hosting our own inference was not enough: now the Hub 4 new inference providers: fal, Replicate, SambaNova Systems, & Together AI. Check model cards on the Hub: you can now, in 1 click, use inference from various providers (cf video demo) Their inference can also be used through our Inference API client. There, you can use either your custom provider key, or your HF token, then billing will be handled directly on your HF account, as a way to centralize all expenses. šŸ’ø Also, PRO users get 2$ inference credits per month! Read more in the announcement šŸ‘‰ https://huggingface.co/blog/inference-providers
reacted to merve's post with šŸ‘ 30 days ago
Oof, what a week! šŸ„µ So many things have happened, let's recap! https://huggingface.co/collections/merve/jan-24-releases-6793d610774073328eac67a9 Multimodal šŸ’¬ - We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG šŸ’— - UI-TARS are new models by ByteDance to unlock agentic GUI control šŸ¤Æ in 2B, 7B and 72B - Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B - MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context - Dataset: Yale released a new benchmark called MMVU - Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark LLMs šŸ“– - DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! šŸ¤Æ - Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B - NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!) Audio šŸ—£ļø - Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B - TangoFlux is a new audio generation model trained from scratch and aligned with CRPO Image/Video/3D Generation āÆļø - Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux - tencent released Hunyuan3D-2, new 3D asset generation from images
View all activity

Organizations

None yet

wsuff's activity

liked 2 models about 1 month ago
liked 3 models about 2 months ago
liked a model 2 months ago
liked a model 3 months ago
liked a model 4 months ago
liked a model 5 months ago
liked a Space 5 months ago
liked a model 5 months ago
liked 4 models 6 months ago
liked a Space 6 months ago
liked 3 models 6 months ago
liked a model 7 months ago