Guido Enrique

Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 804: forward compatibility was attempted on non supported HW

2

Hey guys, i am trying to run the Mistral 7b model using the [guide](https://docs.mistral.ai/self-deployment/vllm/) on the page. I am running: ```bash docker run --gpus all \ -e HF_TOKEN=$HF_TOKEN -p 8000:8000...

Man/mix length Call options not working

1

Model: `llama3` LangchaingoVersion: `v0.1.10` I was trying to use the `llms.WithMaxLength` and `llms.WithMinLength` to set some output limits, but seems like the model doesn't respect these options. ```go callOptions =...

Examples for Tools usage

3

I have noticed that the use of "**functions**" is now deprecated and was replaced for "**tools**". Will be pretty nice to update the examples dir in the repo adding examples...