Locally run DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Wen

Welcome • User Guide
ToS • Privacy • Canary
Donate • Bugs • License

©2025 Poal.co

443

•

Locally run DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Wen (ollama.com)

(post is archived)

You are currently inside a comment thread.

Click here to see all the comments (9).

[–] • 1 pt

It's jewed, that's for sure. I asked it some questions and it regurgitated (((answers))). The problem is that the English speaking world is so brainwashed all of the training data is kiked by default.

parent
link

(post is archived)

You can claim this sub in /s/subrequest