Comment by dsrtslnd23 13 hours ago will this be open weights? 5 comments dsrtslnd23 Reply moonu 12 hours ago I imagine this is based on their 'Thinking with Visual Primitives' paper, and they had mentioned that the weights would be released for that dares2573 12 hours ago I believe so. Openness has always been a consistent tradition of DeepSeek griffiths 12 hours ago This is something I would like to know as well.But if not, does anybody know a recommended way to attach vision to deepseek flash (on a self-hosted infrastructure)? traverseda 12 hours ago Generally you just add a vision model as an MCP server like this: https://github.com/DavidEasden/opencode-vision dannyw 7 hours ago I would probably just give it a few days.Deepseek is usually very good with open weights, they don't necessarily drop immediately, sometimes in a few hours, sometimes in a couple days.
moonu 12 hours ago I imagine this is based on their 'Thinking with Visual Primitives' paper, and they had mentioned that the weights would be released for that
griffiths 12 hours ago This is something I would like to know as well.But if not, does anybody know a recommended way to attach vision to deepseek flash (on a self-hosted infrastructure)? traverseda 12 hours ago Generally you just add a vision model as an MCP server like this: https://github.com/DavidEasden/opencode-vision dannyw 7 hours ago I would probably just give it a few days.Deepseek is usually very good with open weights, they don't necessarily drop immediately, sometimes in a few hours, sometimes in a couple days.
traverseda 12 hours ago Generally you just add a vision model as an MCP server like this: https://github.com/DavidEasden/opencode-vision
dannyw 7 hours ago I would probably just give it a few days.Deepseek is usually very good with open weights, they don't necessarily drop immediately, sometimes in a few hours, sometimes in a couple days.
I imagine this is based on their 'Thinking with Visual Primitives' paper, and they had mentioned that the weights would be released for that
I believe so. Openness has always been a consistent tradition of DeepSeek
This is something I would like to know as well.
But if not, does anybody know a recommended way to attach vision to deepseek flash (on a self-hosted infrastructure)?
Generally you just add a vision model as an MCP server like this: https://github.com/DavidEasden/opencode-vision
I would probably just give it a few days.
Deepseek is usually very good with open weights, they don't necessarily drop immediately, sometimes in a few hours, sometimes in a couple days.