Wladastic
Wladastic
@hqnicolas deepseek is horrible for this. I dont even get a proper JSON, I found a few to be working perfectly: - gemma it 2B q8_0 gguf - Mistral 7b...
@hqnicolas totally forgot to test gemma:7b-IT How does it run? 2B is similar speed to mistral. Oh forgot one model above: Capybara Hermes Mistral 7B is outstandingly great but Mistral...
I cannot confirm this with gpt-pilot. For Gpt-Pilot what worked best now is still: nous-hermes 2 pro 7b gguf with Q8_0 Quant But very important: set n_batch and alpha value...
@piwi3910 Yes I do. To fix this issue you have to edit the invalid_json.prompt which is inside gpt-pilot/pilot/prompts/utils/invalid_json.prompt The last sentence in there is stupid, as giving negative examples is...
@phalexo The code is runnable. Gpt-Pilot (no difference to gpt-pilot, my iphone kept adding Caps) works best with the non quantized version of Mistral-7B v0.2 and Hermes 2 Pro. You...
It does work, these models do generate actual code. the quantised models sometimes get stuck if they produce too much context but the unquantised just so not produce more than...
There is not only ollama and litellm. I use both oobabooga text gen webui with api enabled which emulates the openai api. LMStudio and I wrote my own adapter based...
It still doesn't work because autogpt cannot be imported. Or is that another issue?
same error here, you can fix it by editing the import, but just a dirty fix
you can use my branch "dirty-fix-imports" here https://github.com/Wladastic/Auto-GPT