94bb494nd41f

LoRA Training CPU not working, llama_tokenize: too many tokens

1

Hey there, i tried to replicate what [bublint](https://github.com/bublint/ue5-llama-lora) did, creating a lora based on some documentation, but its simply not working. Is it because i am running a quantized model...

I tried the following models: ``` MODEL_NAME = 'ggml-vicuna-7b-q4_0.bin' MODEL_PATH = r"D:\\ggml-vicuna-7b-q4_0.bin" MODEL_NAME = 'GPT4All-13B-snoozy.ggmlv3.q4_1.bin' MODEL_PATH = r"D:\\GPT4All-13B-snoozy.ggmlv3.q4_1.bin" MODEL_NAME = 'ggml-old-vic7b-q4_0.bin' MODEL_PATH = r"C:\\Users\\elnuevo\\Downloads\\ggml-old-vic7b-q4_0.bin" ``` But only the GPT4All models...

ImportError: cannot import name 'download_loader' from 'llama_index'

1

so i did a fresh install (pip install -r requirements.txt) in conda and stumbled across this error As you might see in my profile i do not open issues that...

Featurerequest: ConversationalRetrival and definition of chain_type

8

I think conversationalRetrival would be a great feature on this awesome project. https://python.langchain.com/docs/modules/chains/popular/chat_vector_db Unfortunately i am not good enough to make it work, i dont know how to pass the...

I switched the chain_type to "map_rerank" and got the first of my three answers but afterwards i got this error. Seems like there is an update of `apply_and_parse` necessary? ```...