Chatbot Arena issues | Ecosyste.ms: OpenCollective

My model

github.com/lm-sys/FastChat - tklentz opened this pull request 8 months ago

Store Images Remotely on GCS

github.com/lm-sys/FastChat - BabyChouSr opened this pull request 8 months ago

After QLoRA finetuning, the inference output repeat the instruction over and over again

github.com/lm-sys/FastChat - c-steve-wang opened this issue 8 months ago

Fix Metharme System Message

github.com/lm-sys/FastChat - xzuyn opened this pull request 8 months ago

[Leaderboard] Wrong Link for GPT-4-0125-Preview

github.com/lm-sys/FastChat - HuanzhiMao opened this issue 8 months ago

Add support for hkunlp - Instructor models for generating embeddings

github.com/lm-sys/FastChat - dawu415 opened this pull request 8 months ago

Grok-1 Model

github.com/lm-sys/FastChat - deadpipe opened this issue 8 months ago

fix yuan2 generation bug

github.com/lm-sys/FastChat - wangpengfei1013 opened this pull request 8 months ago

Developers, could you please add support for the Telechat model in FastChat?

github.com/lm-sys/FastChat - Chtholly1 opened this issue 8 months ago

Voting is possible after an error

github.com/lm-sys/FastChat - mimi89999 opened this issue 8 months ago

Inquiry about MTBench

github.com/lm-sys/FastChat - endNone opened this issue 8 months ago

The review has become too strict

github.com/lm-sys/FastChat - qyczz opened this issue 8 months ago

update chatbot_arena_conversations dataset

github.com/lm-sys/FastChat - Jannchie opened this issue 8 months ago

if len(chunk["choices"]) == 0: KeyError: 'choices'

github.com/lm-sys/FastChat - xunmenglt opened this issue 8 months ago

run controller it stop like that,It was normal yesterday

github.com/lm-sys/FastChat - maogeigei opened this issue 8 months ago

upload reference file for gpt-4-0125-preview as judge to mitigate wrong reference answers by gpt-4

github.com/lm-sys/FastChat - Zhilin123 opened this pull request 8 months ago

Add optional remote data logger

github.com/lm-sys/FastChat - simon-mo opened this pull request 8 months ago

Rate Limit for GPT-4-1106-preview, GPT-4-Turbo-Browsing and GPT-4-0613 keep getting exceeded on chat.lmsys.org??

github.com/lm-sys/FastChat - youself64github opened this issue 8 months ago

Unreachable code in `get_worker_address`

github.com/lm-sys/FastChat - cinjon opened this issue 8 months ago

HTML injection of the web prompt: possible safety issue?

github.com/lm-sys/FastChat - surak opened this issue 8 months ago

RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'

github.com/lm-sys/FastChat - gaurikasar opened this issue 8 months ago

using --device=xpu

github.com/lm-sys/FastChat - tmatschewski opened this issue 8 months ago

Can fastchat support multiple model calls?

github.com/lm-sys/FastChat - empty2enrich opened this issue 8 months ago

[updated] add consistency-llm, a new generation parallel decoder LLMs

github.com/lm-sys/FastChat - snyhlxde1 opened this pull request 8 months ago

[updated] add consistency-llm, a new generation parallel decoder LLMs

github.com/lm-sys/FastChat - snyhlxde1 opened this pull request 8 months ago

add consistency-llm, a new generation parallel decoder LLMs

github.com/lm-sys/FastChat - snyhlxde1 opened this pull request 8 months ago

Document diverged OpenAI API

github.com/lm-sys/FastChat - freddyheppell opened this issue 8 months ago

Cohere Command-R

github.com/lm-sys/FastChat - sanderland opened this pull request 8 months ago

Integrate IPEX-LLM into serve worker

github.com/lm-sys/FastChat - gc-fu opened this pull request 8 months ago

error Inference on for long-context text

github.com/lm-sys/FastChat - ZhangYuanhan-AI opened this issue 8 months ago

Add support for new IBM models (labradorite and merlinite)

github.com/lm-sys/FastChat - shivchander opened this pull request 8 months ago

`fastchat.serve.controller` stops working after a while

github.com/lm-sys/FastChat - PyroGenesis opened this issue 8 months ago

update: Support Yuan2.0 for a new version [Yuan2-2B-Februa-hf]

github.com/lm-sys/FastChat - cauwulixuan opened this pull request 8 months ago

TypeError: `dumps_kwargs` keyword arguments are no longer supported.

github.com/lm-sys/FastChat - kungfulei opened this issue 8 months ago

[#3054] add documentation and trainig file for train_with_template

github.com/lm-sys/FastChat - christobill opened this pull request 8 months ago

fix: garbled Chinese in the conv.json

github.com/lm-sys/FastChat - DSYZayn opened this pull request 8 months ago

support for claude-3

github.com/lm-sys/FastChat - tryumanshow opened this pull request 8 months ago

vllm_worker add multi-lora support

github.com/lm-sys/FastChat - wsvn53 opened this pull request 8 months ago

Is Codellama-70B-Instruct-hf now supported?

github.com/lm-sys/FastChat - sekhar-hari opened this issue 8 months ago

FastChat is failing while handling the returned responses from OpenAI GPT model

github.com/lm-sys/FastChat - sekhar-hari opened this issue 8 months ago

fix(llm_judge): Fix display issues in qa_browser

github.com/lm-sys/FastChat - dave-tucker opened this pull request 8 months ago

SGLang worker does not expose embeddings.

github.com/lm-sys/FastChat - surak opened this issue 8 months ago

add tensorRT model worker

github.com/lm-sys/FastChat - WHDY opened this pull request 8 months ago

Add MT Bench

github.com/lm-sys/FastChat - jasonlee-sf opened this pull request 8 months ago

feat: support Consistency-llm, a new generation Large Language Model developed by parallel Jacobi decoding

github.com/lm-sys/FastChat - rlsu9 opened this pull request 8 months ago

这个项目是停止更新了么？很久没看到新的更新

github.com/lm-sys/FastChat - leoterry-ulrica opened this issue 8 months ago

How do I submit my API endpoint to you?

github.com/lm-sys/FastChat - dyyzhmm opened this issue 8 months ago

why not have log in conversion history？ hope add log info

github.com/lm-sys/FastChat - sjyttkl opened this issue 8 months ago

Exllama output continues conversation

github.com/lm-sys/FastChat - TranChProfessional opened this issue 8 months ago

No module named 'fastchat.protocol'

github.com/lm-sys/FastChat - maceygo opened this issue 8 months ago

Automatic truncation input messages by model max content length

github.com/lm-sys/FastChat - Ox0400 opened this issue 8 months ago

sglang_worker doesn't work for GPTQ models

github.com/lm-sys/FastChat - thiner opened this issue 8 months ago

refactor: Change synchronous requests to aiohttp

github.com/lm-sys/FastChat - phil-park opened this pull request 8 months ago

issues trying to run FastChat with '--device mps' option

github.com/lm-sys/FastChat - sulph68 opened this issue 8 months ago

Whether to support tools invocation

github.com/lm-sys/FastChat - leoterry-ulrica opened this issue 8 months ago

Fix chatglm that does not call model.eval() while load from adapter, and improve it's generation process

github.com/lm-sys/FastChat - p208p2002 opened this pull request 8 months ago

Add YandexGPT API support

github.com/lm-sys/FastChat - thefacetakt opened this pull request 8 months ago

Agreement Computation - Have you considered using Krippendorff's Alpha?

github.com/lm-sys/FastChat - Br1c0lage opened this issue 8 months ago

不太理解？我想用到自己部署的开源模型的tokenier，应该怎么用接口怎么调用呢？

github.com/lm-sys/FastChat - liujia0321 opened this issue 8 months ago

About special tokens

github.com/lm-sys/FastChat - Changgeng-Wei opened this issue 8 months ago

Need to support Qwen1.5-72B-Chat 32k token?

github.com/lm-sys/FastChat - ggservice007 opened this issue 8 months ago

gradio_web_server_multi fails

github.com/lm-sys/FastChat - paroj opened this issue 8 months ago

为什么不更新了？

github.com/lm-sys/FastChat - 1986smalltiger opened this issue 8 months ago

when inferencing the deepspeed saved model, the output is messy

github.com/lm-sys/FastChat - renatz opened this issue 8 months ago

Qwen2 On NPU 910B Error

github.com/lm-sys/FastChat - cason0126 opened this issue 8 months ago

Support LoRA adapters for vLLM worker

github.com/lm-sys/FastChat - andresd95 opened this issue 8 months ago

ChatGLM3-6b Compatibility is expected as soon as possible.

github.com/lm-sys/FastChat - 7010G opened this issue 8 months ago

AttributeError: 'Encoding' object has no attribute 'num_tokens'

github.com/lm-sys/FastChat - 631068264 opened this issue 8 months ago

stop_str not working for vllm_worker

github.com/lm-sys/FastChat - congchan opened this issue 8 months ago

urllib3.exceptions.newconnectionerror

github.com/lm-sys/FastChat - Yinglibo123 opened this issue 8 months ago

TypeError: Object of type Tensor is not JSON serializable

github.com/lm-sys/FastChat - c-steve-wang opened this issue 8 months ago

Bugfix: Fix issues with streaming

github.com/lm-sys/FastChat - verena-hallitschke opened this pull request 8 months ago

Why don't I get any response when I execute python3 -m fastchat.serve.cli --model-path my model path?

github.com/lm-sys/FastChat - DAAworld opened this issue 8 months ago

Support `--chat-template` for vLLM model worker

github.com/lm-sys/FastChat - thiner opened this issue 8 months ago

Add yandexgpt

github.com/lm-sys/FastChat - thefacetakt opened this pull request 8 months ago

Fix mismatched output in web server

github.com/lm-sys/FastChat - sthemeow opened this pull request 8 months ago

Gradio web server shows error

github.com/lm-sys/FastChat - sthemeow opened this issue 8 months ago

Compatibility Issue with Prefix-Tuned Models using PEFT in FastChat

github.com/lm-sys/FastChat - fzalkow opened this issue 9 months ago

Feature: add guidance support for fastchat

github.com/lm-sys/FastChat - linkedlist771 opened this pull request 9 months ago

Support for cosmosage

github.com/lm-sys/FastChat - surak opened this pull request 9 months ago

API call to export chat logs for the server as a whole or a specific workspace.

github.com/lm-sys/FastChat - mark3apps opened this issue 9 months ago

testing google colab example in repo

github.com/lm-sys/FastChat - silvacarl2 opened this issue 9 months ago

Add Orion-14B template and adapter

github.com/lm-sys/FastChat - renillhuang opened this pull request 9 months ago

Why is controller's heart beat thread daemon set to False?

github.com/lm-sys/FastChat - MichelDucartier opened this issue 9 months ago

update bt code

github.com/lm-sys/FastChat - infwinston opened this pull request 9 months ago

Invoke Google PaLM2 models

github.com/lm-sys/FastChat - sekhar-hari opened this issue 9 months ago

Add basic support of mamba-chat

github.com/lm-sys/FastChat - wln20 opened this pull request 9 months ago

PII Filtering

github.com/lm-sys/FastChat - lisadunlap opened this pull request 9 months ago

add system message support for train.py/train_yuan2.py

github.com/lm-sys/FastChat - Force1ess opened this pull request 9 months ago

add system message support for train.py/train_yuan2.py

github.com/lm-sys/FastChat - Force1ess opened this pull request 9 months ago

fastapi and gradio version

github.com/lm-sys/FastChat - congchan opened this issue 9 months ago

[WIP] Data PII filtering

github.com/lm-sys/FastChat - lisadunlap opened this pull request 9 months ago

Unable to run worker for StripedHyena-Nous-7B

github.com/lm-sys/FastChat - kenneth-miura opened this issue 9 months ago

OpenAI key relay

github.com/lm-sys/FastChat - enochlev opened this issue 9 months ago

Add Gemma

github.com/lm-sys/FastChat - BabyChouSr opened this pull request 9 months ago

In order to support the development of agents, I hope that officials can add support for function roles to dialogue templates.

github.com/lm-sys/FastChat - shell-nlp opened this issue 9 months ago

Support CogVLM & Qwen-VL

github.com/lm-sys/FastChat - Lanture1064 opened this issue 9 months ago

support https://huggingface.co/google/gemma-7b & gemma-2b

github.com/lm-sys/FastChat - yanjian1978 opened this issue 9 months ago

When I call the api '/v1/chat/completions' of API Server, it response incomplete results, but vllm's api response complete results

github.com/lm-sys/FastChat - coreyho opened this issue 9 months ago

vllm api will randomly generate answers slowly when applying asynchronous parallel calls

github.com/lm-sys/FastChat - qy1026 opened this issue 9 months ago