← Back to context Comment by dsrtslnd23 11 hours ago will this be open weights? 5 comments dsrtslnd23 Reply dares2573 10 hours ago I believe so. Openness has always been a consistent tradition of DeepSeek moonu 10 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 11 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 11 hours ago Generally you just add a vision model as an MCP server like this: https://github.com/DavidEasden/opencode-vision dannyw 5 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 10 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 11 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 11 hours ago Generally you just add a vision model as an MCP server like this: https://github.com/DavidEasden/opencode-vision dannyw 5 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 11 hours ago Generally you just add a vision model as an MCP server like this: https://github.com/DavidEasden/opencode-vision
dannyw 5 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 believe so. Openness has always been a consistent tradition of DeepSeek
I imagine this is based on their 'Thinking with Visual Primitives' paper, and they had mentioned that the weights would be released for that
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.