Qualzz

https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/chains/summarize/refine_prompts.py I don't actively use langchain right now, but by looking at the file itself, it seems to miss a new line or an empty space "We have the opportunity...

Can someone help me to understand what is the expected answer from the agent executor ? For exemple: ``` I will multiply 45 by 224 Action: Python REPL Action Input:...

Seems like there is some issue with the dependencies version used by pyannote

Confirming the same issue with high 8gbps speed. Downloading mixtral model in a few seconds at around 800mb/s then at 98/99% is goes down to around 100Kb/s and takes forever....

Is there a reason why I have " Loading model" everytime I start a new generation ( even if I don't change the model ) It takes a lot of...

yes, another way is just to have all your url separated by a comma. url1, url2, url3 Paste this in the url textbox, and they should be parsed correctly

There is also the vision model: https://huggingface.co/microsoft/Phi-3-vision-128k-instruct/

Try to just type "python3" in your terminal and see if it's installed or not. If it's not, you may have the microsoft store proposing to install it. Install it,...

llama_model_load: llama_model_load: tensor 'tok_embeddings.weight' has wrong size in model file For 30B

For those having the same issue you can try formatting your dataset like this: ```[ { "conversations": [ { "from": "human", "value": "Lorem ipsum" }, { "from": "gpt", "value": "Lorem...