Ranadheer Malla
Ranadheer Malla
which model are you using?
> A basic LangChainJS package for Alpaca is here https://github.com/linonetwo/langchain-alpaca Great!! but would be nicer if there's a python wrapper
you can use the huggingfacepipeline class., something like this ``` from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline from langchain.llms import HuggingFacePipeline model_path = 'your_local_model_path' tokenizer = AutoTokenizer.from_pretrained(model_path) model = AutoModelForCausalLM.from_pretrained(model_path) alpaca_pipe...
@merrymercy The process of adding models to the system is not difficult, but it becomes complicated when each model has its own "end-of-sequence" token that it was trained with. To...
@Halflifefa set max-gpu-memory, and provide the max memory you can allocate. Also, use another argument, --gpus 0,1,2,3. i think the later should work better
this is a really cool implementation. waiting for this to unlock.