Chatbot Arena issues | Ecosyste.ms: OpenCollective

RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'

github.com/lm-sys/FastChat - Gnomesenpai opened this issue about 1 year ago

zephyr-7b-alpha

github.com/lm-sys/FastChat - luisrguerra opened this issue about 1 year ago

Add Zephyr 7B Alpha

github.com/lm-sys/FastChat - lewtun opened this pull request about 1 year ago

Improve docs

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

How to determine the number of GPUs needed？

github.com/lm-sys/FastChat - 2018211801 opened this issue over 1 year ago

Question using Openai-api compatible API service to serve llama-2-7b

github.com/lm-sys/FastChat - Junpliu opened this issue over 1 year ago

move BaseModelWorker outside serve.model_worker to make it independent

github.com/lm-sys/FastChat - liunux4odoo opened this pull request over 1 year ago

模型文件和本项目部署在服务商，我想在本地使用tokenizer，可以使用这个项目实例化一个tokenizer？

github.com/lm-sys/FastChat - ye7love7 opened this issue over 1 year ago

Fix Mistral template

github.com/lm-sys/FastChat - normster opened this pull request over 1 year ago

How to get logs for every x number of steps instead of epochs

github.com/lm-sys/FastChat - code-x-0018 opened this issue over 1 year ago

What's model deluxe-chat-v1 ?

github.com/lm-sys/FastChat - xioxu opened this issue over 1 year ago

gen_model_answer.py generates the phenomenon of multiple conversations

github.com/lm-sys/FastChat - wangtong2020 opened this issue over 1 year ago

Github copilot compatibility

github.com/lm-sys/FastChat - surak opened this issue over 1 year ago

Update Dockerfile

github.com/lm-sys/FastChat - dubaoquan404 opened this pull request over 1 year ago

Launch model worker with local weights

github.com/lm-sys/FastChat - CohenQU opened this issue over 1 year ago

Fix arena

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

Please support fastllm

github.com/lm-sys/FastChat - gaoxiao opened this issue over 1 year ago

Mistral template is wrong

github.com/lm-sys/FastChat - normster opened this issue over 1 year ago

Can be used with Mistral Model?

github.com/lm-sys/FastChat - rajveer43 opened this issue over 1 year ago

openai api server - last two api calls not protected with check_api_key when used with api keys

github.com/lm-sys/FastChat - stelterlab opened this issue over 1 year ago

Ask about the usage of template

github.com/lm-sys/FastChat - coranholmes opened this issue over 1 year ago

add support for bedrock, togetherai, huggingface tgi, replicate, ai21, cohere, ai21

github.com/lm-sys/FastChat - krrishdholakia opened this pull request over 1 year ago

replace os.getenv with os.path.expanduser because the first one doesn…

github.com/lm-sys/FastChat - khalil-Hennara opened this pull request over 1 year ago

Can't able to get Prediction with Multi-GPU, but working fine in case of Single GPU

github.com/lm-sys/FastChat - rajvirdhakhada7 opened this issue over 1 year ago

LongChatV1.5-7B-32K with FlashAtten2 OOMs on inference

github.com/lm-sys/FastChat - jmzeng opened this issue over 1 year ago

move BaseModelWorker outside serve.model_worker to make it independent

github.com/lm-sys/FastChat - liunux4odoo opened this pull request over 1 year ago

Add StreamingLLM to improve streaming performance

github.com/lm-sys/FastChat - BabyChouSr opened this issue over 1 year ago

add Llama2ChangAdapter

github.com/lm-sys/FastChat - lcw99 opened this pull request over 1 year ago

Fix for single turn dataset

github.com/lm-sys/FastChat - toslunar opened this pull request over 1 year ago

questions in vicuna_bench with reference_answer cannot run

github.com/lm-sys/FastChat - toslunar opened this issue over 1 year ago

Release v0.2.30

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

Update monitor & plots

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM @fschat 0.2.29, torch 2.0.1+cu118, transformers 4.33.3

github.com/lm-sys/FastChat - ZealHua opened this issue over 1 year ago

jetson orin agx

github.com/lm-sys/FastChat - MrBrabus75 opened this issue over 1 year ago

Optimize for proper flash attn causal handling

github.com/lm-sys/FastChat - siddartha-RE opened this pull request over 1 year ago

does python3 -m fastchat.serve.test_message support other model?

github.com/lm-sys/FastChat - lambda7xx opened this issue over 1 year ago

release and tags are not in sync

github.com/lm-sys/FastChat - bufferoverflow opened this issue over 1 year ago

Add metharme (pygmalion) conversation template

github.com/lm-sys/FastChat - AlpinDale opened this pull request over 1 year ago

Third Party UI Example

github.com/lm-sys/FastChat - enochlev opened this pull request over 1 year ago

Update train code to support the new tokenizer

github.com/lm-sys/FastChat - Ying1123 opened this pull request over 1 year ago

Update links to lmsys-chat-1m

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

Using `--device mps` results in `RuntimeError: PyTorch is not linked with support for mps devices`

github.com/lm-sys/FastChat - ngreve opened this issue over 1 year ago

support Stable Beluga 2

github.com/lm-sys/FastChat - lbgws2 opened this issue over 1 year ago

Vicuna template may cause the tokenization mismatch warning

github.com/lm-sys/FastChat - Kong-Aobo opened this issue over 1 year ago

Update vllm_worker.py fix bug #2491 vllm 0.2.0 version from vllm.engine.async_l…

github.com/lm-sys/FastChat - exceedzhang opened this pull request over 1 year ago

Update README.md

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

vllm_worker.py run error on vllm0.2.0

github.com/lm-sys/FastChat - exceedzhang opened this issue over 1 year ago

Fail to start vllm_worker for codellama/CodeLlama-7b-Instruct-hf on two T4 gpus

github.com/lm-sys/FastChat - bugzyz opened this issue over 1 year ago

Pass root_path argument in web_server.py

github.com/lm-sys/FastChat - pweglik opened this issue over 1 year ago

Update vllm_worker.py

github.com/lm-sys/FastChat - shuishu opened this pull request over 1 year ago

ValueError: Tokenizer class QWenTokenizer does not exist or is not currently imported.

github.com/lm-sys/FastChat - thiner opened this issue over 1 year ago

Can't load model Qwen-14B-Chat-Int4

github.com/lm-sys/FastChat - dijkstra-mose opened this issue over 1 year ago

Fix chunk handling when partial chunks are returned

github.com/lm-sys/FastChat - siddartha-RE opened this pull request over 1 year ago

Update openai_api_server.py to add an SSL option

github.com/lm-sys/FastChat - brandonbiggs opened this pull request over 1 year ago

Add Mistral AI instruction template

github.com/lm-sys/FastChat - lerela opened this pull request over 1 year ago

Update vllm_worker.py

github.com/lm-sys/FastChat - shuishu opened this pull request over 1 year ago

Output in a defined JSON format

github.com/lm-sys/FastChat - rounak610 opened this issue over 1 year ago

能否8bit量化加载启动Qwen14b的？fastchat代码中限定了使用bin格式，而qwen14b只提供了safetensor格式。

github.com/lm-sys/FastChat - ye7love7 opened this issue over 1 year ago

Add conversation templates for ultralm

github.com/lm-sys/FastChat - lifan-yuan opened this pull request over 1 year ago

HOME Environment Variable Does Not Exist on Windows 11

github.com/lm-sys/FastChat - Skareeg opened this issue over 1 year ago

Model does not load in Docker

github.com/lm-sys/FastChat - Rachneet opened this issue over 1 year ago

support finetune on Qwen14B

github.com/lm-sys/FastChat - lucasjinreal opened this issue over 1 year ago

very strange?RTX3090 load vicuna-7b,with 22g of video memory usage

github.com/lm-sys/FastChat - ye7love7 opened this issue over 1 year ago

help！ llama2-13b use vllm_worker with two A100(80g); the RayWoker throw an exceptions

github.com/lm-sys/FastChat - azureboot opened this issue over 1 year ago

Run the qwen model and the response is messy

github.com/lm-sys/FastChat - lonngxiang opened this issue over 1 year ago

CodeLlama-Python does not work

github.com/lm-sys/FastChat - surak opened this issue over 1 year ago

help!vllm with qwen-7b-chat fail:RuntimeError: Failed to load the model config.

github.com/lm-sys/FastChat - ye7love7 opened this issue over 1 year ago

Max retries exceeded with url: /get_worker_address (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f4228f511b0>: Failed to establish a new connection: [Errno 111] Connection refused

github.com/lm-sys/FastChat - lonngxiang opened this issue over 1 year ago

fix typo quantization

github.com/lm-sys/FastChat - asaiacai opened this pull request over 1 year ago

how to get stream output when run python3 -m fastchat.serve.api?

github.com/lm-sys/FastChat - lonngxiang opened this issue over 1 year ago

[model_worker] should `worker-address` argument need to be changed when `host` or `port` arguments are changed?

github.com/lm-sys/FastChat - hi-jin opened this issue over 1 year ago

ValueError: Tokenizer class BaichuanTokenizer does not exist or is not currently imported.

github.com/lm-sys/FastChat - lonngxiang opened this issue over 1 year ago

[Fine-Tuning Fail]: Problem Running FastChat T5 fine-tuning

github.com/lm-sys/FastChat - pcchen-ntunlp opened this issue over 1 year ago

Fix falcon chat template

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

vllm worker awq quantization update

github.com/lm-sys/FastChat - dongxiaolong opened this pull request over 1 year ago

Potential Issue of Vicuna v1.5 Training

github.com/lm-sys/FastChat - xingyaoww opened this issue over 1 year ago

Show terms of use as an JS alert

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

LLama 2 finetuning on multi-GPU with long context length

github.com/lm-sys/FastChat - amant555 opened this issue over 1 year ago

ValueError: Found modules on cpu/disk. Using Exllama backend requires all the modules to be on GPU.You can deactivate exllama backend by setting `disable_exllama=True` in the quantization config objec

github.com/lm-sys/FastChat - dinchu opened this issue over 1 year ago

No module named 'transformers' in docker-compose.yml

github.com/lm-sys/FastChat - theUpsider opened this issue over 1 year ago

llama-2 70b model using openai_api_server chat completions api or gradio interface times out

github.com/lm-sys/FastChat - harshitpatni opened this issue over 1 year ago

Huggingface api worker

github.com/lm-sys/FastChat - hnyls2002 opened this pull request over 1 year ago

Add ExllamaV2 Inference Framework Support.

github.com/lm-sys/FastChat - leonxia1018 opened this pull request over 1 year ago

Add Exllama2 Inference Framework Support.

github.com/lm-sys/FastChat - leonxia1018 opened this pull request over 1 year ago

When using the new version of 'mtbench', I encountered an issue

github.com/lm-sys/FastChat - endNone opened this issue over 1 year ago

enable quantization support for the VLLM worker

github.com/lm-sys/FastChat - dongxiaolong opened this issue over 1 year ago

DLL importing issues on windows

github.com/lm-sys/FastChat - majidbhatti opened this issue over 1 year ago

Release v0.2.29

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

Missing possibility for GET request against model_workers for "liveness" and "readiness" signals for kubernetes

github.com/lm-sys/FastChat - aecorn opened this issue over 1 year ago

Add Optional SSL Support to controller.py

github.com/lm-sys/FastChat - brandonbiggs opened this pull request over 1 year ago

Error while using RetrievalQA chain type of Langchain for vector retrieval using FastChat LLM model which is hosted on Endpoint(GPU machine).

github.com/lm-sys/FastChat - Smitraj007 opened this issue over 1 year ago

Update UI

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

Unable to Load Llama-2-70B-chat-GPTQ

github.com/lm-sys/FastChat - chengyanwu opened this issue over 1 year ago

openai.error.APIConnectionError

github.com/lm-sys/FastChat - 385628424 opened this issue over 1 year ago

block_css not work well for Chatbot

github.com/lm-sys/FastChat - LiuZhihhxx opened this issue over 1 year ago

Openai interface add use beam search and best of 2

github.com/lm-sys/FastChat - leiwen83 opened this pull request over 1 year ago

[WIP] Add microsoft/phi-1_5

github.com/lm-sys/FastChat - BabyChouSr opened this pull request over 1 year ago

Data cleaning scripts for dataset release

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago

How do I load the bge model and start the service?

github.com/lm-sys/FastChat - asenasen123 opened this issue over 1 year ago

Improve docs

github.com/lm-sys/FastChat - merrymercy opened this pull request over 1 year ago