dan su's picture

1 2 3

dan su

sudanenator

·

AI & ML interests

None yet

Recent Activity

reacted to danielhanchen's post with 🔥 4 days ago

Deepseek V3, including GGUF + bf16 versions are now uploaded! Includes 2, 3, 4, 5, 6 and 8-bit quantized versions. GGUFs: https://huggingface.co/unsloth/DeepSeek-V3-GGUF bf16: https://huggingface.co/unsloth/DeepSeek-V3-bf16 Min. hardware requirements to run: 48GB RAM + 250GB of disk space for 2-bit. See how to run them with examples and the full collection: https://huggingface.co/collections/unsloth/deepseek-v3-all-versions-677cf5cfd7df8b7815fc723c

reacted to reddgr's post with 👀 4 days ago

Major update on the Talking to Chatbots dataset! Expanded the 'wrapped' dataset (one row per chat) to 2.86k records, and the 'unwrapped' version (one row per conversation turn) to 11k records. The main source is my ChatGPT archive with nearly 2 years of chats. It is still a work in progress as I incorporate chats from other sources and qualitative metrics (SCBN) for responses. https://huggingface.co/datasets/reddgr/talking-to-chatbots-unwrapped-chats https://huggingface.co/datasets/reddgr/talking-to-chatbots-chats

View all activity

Organizations

Papers 8

arxiv:2401.13601

arxiv:2309.12792

arxiv:2302.04023

arxiv:2204.09934

models

None public yet

datasets

None public yet