FastChat
FastChat copied to clipboard
lm-sys
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Hi all, I have a service called by `requests.post`, how to host it on the fastchat web ui?
[OpenRouter](https://openrouter.ai/models/google/gemini-pro-1.5) now supports Gemini Pro 1.5, so it should be accessible to the public.
upload reference file for gpt-4-0125-preview as judge to mitigate wrong reference answers by gpt-4
## Why are these changes needed? We (two Applied Scientists with graduate degrees in Artificial Intelligence) recently manually vet through the reference answers for the default gpt-4 judge. To our...
If I run ``` python gen_model_answer.py --model-path openai-community/gpt2-large --model-id gpt2-large ``` under the directory `FastChat/fastchat/llm_judge` I get this error ``` /opt/conda/conda-bld/pytorch_1711403380909/work/aten/src/ATen/native/cuda/Indexing.cu:1237: indexSelectSmallIndex: block: [8,0,0], thread: [86,0,0] Assertion `srcIndex < srcSelectDimSize`...
## Why are these changes needed? This PR adds a new template for H2O-Danube such as: https://huggingface.co/h2oai/h2o-danube2-1.8b-chat Additionally, I have updated a few minor things: - Changed `conv = get_conversation_template(model_id)`...
``` /workspace# python3 -m fastchat.serve.model_worker ... "POST /worker_generate HTTP/1.1" 500 Internal Server Error 2023-12-13 04:01:05 | ERROR | stderr | ERROR: Exception in ASGI application .... 2023-12-13 04:01:07 | ERROR...
I am running the gradio web UI 0.2.36 in a air-gapped Kubernetes cluster. Gradio app cannot start. **Version 0.2.34 used to work without issues.** I tried the following: - setting...
Why is the --device npu parameter fixed to support only one Ascend NPU in code instead of multiple NPUs? ` def generate_stream_gate(self, params):` ` if self.device == "npu":` ` import...
