Brendan King

Top-p sampling returns incorrect/missing log-probabilities in details

3

### System Info I noticed text-generation-inference is providing incorrect log-probabilities in the details whenever top-p sampling is used. I'm running text-generation-inference via docker, using this k8s pod definition on a...

Hi all! In the paper, I noticed this line saying there were 6,500 TaskMaster Dialogues: > The Taskmaster Coffee dataset consists of 6,500 multi-turn conversations, consisting of 20,000 training examples...

Hi all! I was interested in getting the exact training dataset contents for the models available on huggingface ([DIAL-FLANT5-XL](https://huggingface.co/prakharz/DIAL-FLANT5-XL), etc). I see in the README it says it would be...

DFS.py changes causing functions to not be called with ToolLLaMa

1

Hi! I'm working on running ToolLLaMa against the StableToolBench server, and noticed an issue. I am executing the following: ```bash python toolbench/inference/qa_pipeline.py \ --tool_root_dir data_example/toolenv/tools/ \ --backbone_model toolllama \ --model_path...