search

coleam00 / bolt.new-any-llm

Prompt, run, edit, and deploy full-stack web applications using any LLM you want!
https://bolt.new
MIT License
3.93k stars 1.61k forks source link

Update to Gemini exp-1121 #371

Closed kekePower closed 3 hours ago

kekePower commented 13 hours ago

Just saw that Google has updated their experimental model so I had to update it here as well.

champ2050 commented 5 hours ago

@kekePower Could you kindly add these Hugging Face models to the constants file? Place them below the Qwen-32B-Instruct model. The models to add are:

wonderwhy-er commented 3 hours ago

Tested ,works

@kekePower Could you kindly add these Hugging Face models to the constants file? Place them below the Qwen-32B-Instruct model. The models to add are:

  • Qwen/Qwen2.5-72B-Instruct
  • meta-llama/Llama-3.1-70B-Instruct
  • meta-llama/Llama-3.1-405B

We can do another PR for that. Honestly I wanted to invest in to dynamic loading of models better for number of reasons, so that we do not need to make such PRs at all

champ2050 commented 3 hours ago

Sure, that sounds good. Yes, a dynamic approach is much better, especially with so many models and new places offering attractive pricing or even free options.

kekePower commented 1 hour ago

@kekePower Could you kindly add these Hugging Face models to the constants file? Place them below the Qwen-32B-Instruct model. The models to add are:

* Qwen/Qwen2.5-72B-Instruct

* meta-llama/Llama-3.1-70B-Instruct

* meta-llama/Llama-3.1-405B

https://github.com/coleam00/bolt.new-any-llm/pull/380