Spaces:
Running
Running
Model Request: Qwen2-72B
#484
by
flexagontnt
- opened
Qwen2-72B has recently been released and outperforms Llama-3-70B and Mixtral-8x22B in most benchmarks. Possible to add or is the model too big?
Yes! would be awesome!
I'd love to see Qwen2-72b because my system prompts are getting larger than 6k tokens and Qwen2 has a context window as large as Command-R Plus.
We have both Qwen2.5-72B and Qwen2.5-Coder-32B now btw! See them here: https://huggingface.co/chat/models