Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry Paper • 2411.15221 • Published 10 days ago • 20
view post Post 3587 Reply Small yet mighty! 💫We are releasing SmolVLM: a new 2B small vision language made for on-device use, fine-tunable on consumer GPU, immensely memory efficient 🤠 We release three checkpoints under Apache 2.0: SmolVLM-Instruct, SmolVLM-Synthetic and SmolVLM-Base HuggingFaceTB/smolvlm-6740bd584b2dcbf51ecb1f39Learn more from our blog here: huggingface.co/blog/smolvlmThis release comes with a demo, fine-tuning code, MLX integration and TRL integration for DPO 💝Try the demo: HuggingFaceTB/SmolVLMFine-tuning Recipe: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynbAlso TRL integration for DPO 💗 See translation 🔥 12 12 🤗 6 6 🚀 5 5 👀 3 3 +
view article Article Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA May 24, 2023 • 96