Smaller deepseek models?
Are you planning on preparing 7B Qwen DeepSeek R1 or 8B Llama DeepSeek R1 as well?
Would be perfect for ollama. I would even tip you a hundred bucks in btc it if I could run one of these this week.
Sorry, is this a Dolphin version? Or another "uncensored" one?
Could you please push your builds to Ollama repository? So a page like this appears: https://ollama.com/CognitiveComputations
No, they are the original version.
can you share awq command you use for convert this model to awq version,please ?
The demand for uncensored deepseek model everyone could use at home is huge. Is there any progress here?
Apparently this is not even a Dolphin version yet, just a pure fork of R1.
Yet, I've found another author publishing an "abliterated" version here: https://huggingface.co/collections/huihui-ai/deepseek-r1-abliterated-6790ea12ce8c8c4e5df51b7f