Closed sashokbg closed 5 months ago
Passing it the huggingface ID for the regular (non GGUF/quantized) repo works to get the tokenizer. So for Meta-Llama-3-8B-Instruct you'd pass tokenizer="meta-llama/Meta-Llama-3-8B-Instruct"
to your LMQL functions.
from
lmql.model("llama.cpp:/home/alexander/Games2/models/Meta-Llama-3-8B-Instruct.Q5_K_M.gguf",
tokenizer="meta-llama/Meta-Llama-3-8B-Instruct",
endpoint="localhost:9999")
Hello @ChairGraveyard I put the tokenizer as you proposed and also had to accept meta's license and put my huggingface token in ~/.cache/huggingface/token
Thank you for your help !
Hello, I am coming back to this issue to put some additional info. It is also required to install "transformers" dependency that allows lmql to download models from hugging face.
pip install transformers
~/.cache/huggingface/token
Hi, I don't have this token folder/file. It is a txt or something similar? How do I add this in?
Just create it and put inside your token from HF
Hello, I want to test the new Llama 3 8B model locally but I am unable to make it run using the playground since I cannot find a suitable tokenizer.
I run my server like this:
and have the following in my playground
But I get the error message that there is no tokenizer available:
Any tips on what tokenizer should be used ?