[GH-ISSUE #2] can you please share sharded (<2gb / bin) model? #2

New issue

Closed

opened 2026-10-26 21:01:29 +00:00 by bsakaguchi · 2 comments

bsakaguchi commented

2026-10-26 21:01:29 +00:00

Owner

Originally created by @amrrs on GitHub (Nov 29, 2023).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-LLM/issues/2

Thanks for this. The 7B model can be fit in Google colab given there model are tiny pieces.
Example: https://huggingface.co/bn22/Mistral-7B-Instruct-v0.1-sharded

Originally created by @amrrs on GitHub (Nov 29, 2023). Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-LLM/issues/2 Thanks for this. The 7B model can be fit in Google colab given there model are tiny pieces. Example: https://huggingface.co/bn22/Mistral-7B-Instruct-v0.1-sharded

bsakaguchi closed this issue

2026-10-26 21:01:29 +00:00

bsakaguchi commented

2026-10-26 21:01:31 +00:00

Author

Owner

@luofuli commented on GitHub (Feb 4, 2024):

The example link has been 404. And we don't have a plan to share the shaded model. Therefore, I close the issue.

@luofuli commented on GitHub (Feb 4, 2024): The example link has been 404. And we don't have a plan to share the shaded model. Therefore, I close the issue.

bsakaguchi commented

2026-10-26 21:01:31 +00:00

Author

Owner

@amrrs commented on GitHub (Feb 4, 2024):

For anyone else coming here, someone else on HF had already shared a sharded model - https://huggingface.co/notzero/deepseek_sharded/tree/main (I'm not sure of the legitimacy or the content of it, use at your own risk)

@amrrs commented on GitHub (Feb 4, 2024): For anyone else coming here, someone else on HF had already shared a sharded model - https://huggingface.co/notzero/deepseek_sharded/tree/main (I'm not sure of the legitimacy or the content of it, use at your own risk)

bsakaguchi referenced this issue

2026-10-26 21:02:14 +00:00

[GH-ISSUE #75] [Feature Request] Long-context handling, session memory & user-driven insights from extended dialogue #55