DeepSeek-Coder

> Doesn't the deepseek licence completely forbid any use in the EU already? Care to explain? https://deepseeklicense.github.io/ https://github.com/deepseek-ai/DeepSeek-Coder/blob/main/LICE...

deepseek-coder-instruct 6.7B still looks like is better than llama 3 8B on HumanEval [0], and deepseek-coder-instruct 33B still within reach to run on 32 GB Macbook M2 Max - Lamma 3 70B on the other hand will be hard to run locally unless you really have 128GB ram or more. But we will see in the following days how it performs in real life. [0] https://github.com/deepseek-ai/deepseek-coder?tab=readme-ov-...

Deepseek (https://github.com/deepseek-ai/DeepSeek-Coder?tab=readme-ov-...) code is MIT and the model license is available too. edit I should mention that using the Web service Deepseek provides will unceremoniously shutdown terms deemed to be too sensitive. Self hosted models do not appear to be as aggressive.

do you just run it from https://github.com/deepseek-ai/DeepSeek-Coder ?

You would want to test it out manually day to day. That’s always the best. Some models can out score but not actually be “better” when you use it. But there is also the benchmarking: https://github.com/deepseek-ai/deepseek-coder 33B Instruct doesn’t beat 6.7B Instruct by much but maybe those % improvements mean more for your usage. I run 6.7B since I have 16GB RAM. Quantization of the model also makes a difference.