Chatbot Arena issues | Ecosyste.ms: OpenCollective

Chatbot Arena: Add phi-2 and phi-3 models

github.com/lm-sys/FastChat - EwoutH opened this issue 7 months ago

Fix ChatGLM3 format error

github.com/lm-sys/FastChat - gc-fu opened this pull request 7 months ago

[Feature Request] Support for Huggingface Chat Templates

github.com/lm-sys/FastChat - PyroGenesis opened this issue 7 months ago

add chat template for CohereForAI/c4ai-command-r-plus

github.com/lm-sys/FastChat - KehaoWu opened this issue 7 months ago

Fix bug in gradio_web_server.py

github.com/lm-sys/FastChat - renning22 opened this pull request 7 months ago

problem about ascend npu 910A

github.com/lm-sys/FastChat - BruceWang1996 opened this issue 7 months ago

gemini-1.5-pro-api-0409-preview model does not support streaming output

github.com/lm-sys/FastChat - Sn0wo2 opened this issue 7 months ago

Finetuning Llama3-8B fails due to lack of a PAD token in new tokenizer

github.com/lm-sys/FastChat - RDouglasSharp opened this issue 7 months ago

SillyTavern ui? FastChat compatible?

github.com/lm-sys/FastChat - QuinnPiers opened this issue 7 months ago

Please support top_logprobs via API

github.com/lm-sys/FastChat - xufengduan opened this issue 7 months ago

Can support the new model about Llama3

github.com/lm-sys/FastChat - 1737686924 opened this issue 7 months ago

How deepseekcoder6.7b supports streaming output results

github.com/lm-sys/FastChat - 469981325 opened this issue 7 months ago

fastchat模型部署支持qwen1.5吗？

github.com/lm-sys/FastChat - yawzhe opened this issue 7 months ago

dont support CohereForAI/c4ai-command-r-plus-4bit

github.com/lm-sys/FastChat - valueLzy opened this issue 7 months ago

support llama3

github.com/lm-sys/FastChat - gasvn opened this pull request 7 months ago

Change separator in phind conversation template from colon to newline

github.com/lm-sys/FastChat - dannydarvish opened this pull request 7 months ago

adding llama3 template

github.com/lm-sys/FastChat - TJ-Solergibert opened this pull request 7 months ago

[Llama3-Instruct] Conversation template

github.com/lm-sys/FastChat - LeshengJin opened this pull request 7 months ago

Chatbot Arena: Add Reka Edge and Core models

github.com/lm-sys/FastChat - EwoutH opened this issue 7 months ago

GPT-4-turbo MMLU scores?

github.com/lm-sys/FastChat - Duncan-Haywood opened this issue 7 months ago

ValueError: Tokenizer class GemmaTokenizer does not exist or is not currently imported,

github.com/lm-sys/FastChat - 1737686924 opened this issue 7 months ago

Very quick question about rule for handling position bias in Agreement statistics

github.com/lm-sys/FastChat - GradientGuru opened this issue 7 months ago

The fix for the Chinese-Alpaca-2-7B model matches the wrong AlpacaAda…

github.com/lm-sys/FastChat - linstreamer opened this pull request 7 months ago

Can Azure openi api be proxied by fastchat.serve.openai_api_server?

github.com/lm-sys/FastChat - Huyueeer opened this issue 7 months ago

[Feature Request] Pre-built docker image support

github.com/lm-sys/FastChat - zsaladin opened this issue 7 months ago

training data?

github.com/lm-sys/FastChat - silvacarl2 opened this issue 7 months ago

Cannot serve `CohereForAI/c4ai-command-r-plus-4bit`

github.com/lm-sys/FastChat - phisad opened this issue 7 months ago

Which version of gpt-4 is used to generate the mt-bench scores on lmsys leaderboard?

github.com/lm-sys/FastChat - YizeMinimax opened this issue 7 months ago

Will the cache kv become invalid?

github.com/lm-sys/FastChat - oslijunw opened this issue 7 months ago

Support NousResearch/Hermes-2-Pro-Mistral-7B

github.com/lm-sys/FastChat - mikutsky opened this issue 7 months ago

Register SmaugChatAdapter.

github.com/lm-sys/FastChat - arkapal3 opened this pull request 7 months ago

Inaccessible Leaderboard with Screenreader

github.com/lm-sys/FastChat - chigkim opened this issue 7 months ago

启动模型的时候指定gpu报错

github.com/lm-sys/FastChat - ilovecomet opened this issue 7 months ago

Azure OpenAI support for MT-Bench

github.com/lm-sys/FastChat - maxim-saplin opened this pull request 7 months ago

Update README.md

github.com/lm-sys/FastChat - infwinston opened this pull request 7 months ago

MMLU for GPT-4-turbo models?

github.com/lm-sys/FastChat - Duncan-Haywood opened this issue 7 months ago

[BUG] RuntimeError: NPU out of memory. Tried to allocate 268.00 MiB

github.com/lm-sys/FastChat - WangxuP opened this issue 7 months ago

Error in sys.excepthook

github.com/lm-sys/FastChat - SAP-BobJi opened this issue 7 months ago

Reka AI model integration

github.com/lm-sys/FastChat - xvblack opened this pull request 7 months ago

Support Gemini Pro 1.5

github.com/lm-sys/FastChat - NightMachinery opened this issue 7 months ago

Question about gen_model_answer.py with gpt2-large

github.com/lm-sys/FastChat - QiyaoWei opened this issue 7 months ago

Analysis

github.com/lm-sys/FastChat - AsaCooperStickland opened this pull request 7 months ago

H2O-Danube template & minor fixes

github.com/lm-sys/FastChat - psinger opened this pull request 7 months ago

How can I use Multiple NPUs ?

github.com/lm-sys/FastChat - QuentinWang1 opened this issue 7 months ago

upgrade xFasterTransformer support to latest version

github.com/lm-sys/FastChat - a3213105 opened this pull request 7 months ago

Gradio UI 0.2.36 not launching

github.com/lm-sys/FastChat - stephanbertl opened this issue 7 months ago

Frontend svelte-i18n error when chatting with custom API models

github.com/lm-sys/FastChat - acylam opened this issue 7 months ago

[Usage] How to inference with multi-GPUs in single machine? Possible to do batch inference?

github.com/lm-sys/FastChat - ee2110 opened this issue 7 months ago

chore: let conv.message be str if no image provided in request

github.com/lm-sys/FastChat - Lanture1064 opened this pull request 7 months ago

How to register request style api to serve on web UI?

github.com/lm-sys/FastChat - congchan opened this issue 7 months ago

GPU memory keeps growing with more talks, but the GPU memory is not released when the tallk is closed.

github.com/lm-sys/FastChat - 0Xiao0 opened this issue 7 months ago

Experiment26 Model (7B) Better than Starling Beta? Please Add.

github.com/lm-sys/FastChat - JamesClarke7283 opened this issue 7 months ago

multi-node training not working

github.com/lm-sys/FastChat - ashmalvayani opened this issue 7 months ago

Update README.md

github.com/lm-sys/FastChat - infwinston opened this pull request 7 months ago

[feature] support codellama 70b

github.com/lm-sys/FastChat - kota-iizuka opened this pull request 7 months ago

Add code tagger

github.com/lm-sys/FastChat - Naman-ntc opened this pull request 7 months ago

when finetune 13B model it will have error on safe_save_model_for_hf_trainer

github.com/lm-sys/FastChat - Oscarjia opened this issue 7 months ago

How to set random seed number to get consistent output on Vicuna-13b-v1.3?

github.com/lm-sys/FastChat - ee2110 opened this issue 7 months ago

Print SEED Value for each response [Feature request]

github.com/lm-sys/FastChat - deadpipe opened this issue 7 months ago

Better device_map and max_memory for loading vicuna model

github.com/lm-sys/FastChat - sleeepeer opened this issue 7 months ago

Inconsistency of prompt for llama2

github.com/lm-sys/FastChat - XuHwang opened this issue 7 months ago

JSON decode error

github.com/lm-sys/FastChat - 0sengseng0 opened this issue 7 months ago

Add support for Smaug-2.

github.com/lm-sys/FastChat - arkapal3 opened this pull request 7 months ago

An idea for multi-response battles

github.com/lm-sys/FastChat - endolith opened this issue 7 months ago

如何进行多卡多机，有没有详细教程

github.com/lm-sys/FastChat - bravelyi opened this issue 7 months ago

Make Claude 3 haiku as default model, instead sonnet

github.com/lm-sys/FastChat - DarkWyvBat opened this issue 7 months ago

It is possible to run a worker using API-based models

github.com/lm-sys/FastChat - harryzwh opened this issue 7 months ago

is it possible to use the same controller and openai_api_server for multiple model_worker ?

github.com/lm-sys/FastChat - yananchen1989 opened this issue 7 months ago

[embedding model & connect with Langchain] "POST /v1/embeddings HTTP/1.1" 500 Internal Server Error

github.com/lm-sys/FastChat - panxnan opened this issue 7 months ago

Remove Bard disclaimer

github.com/lm-sys/FastChat - abitrolly opened this pull request 7 months ago

Add `--max-model-len` param and description to `serve.vllm_worker`?

github.com/lm-sys/FastChat - Lanture1064 opened this issue 7 months ago

support repetition_penalty param in vllm_worker

github.com/lm-sys/FastChat - cybergeek2077 opened this pull request 8 months ago

Change the controller heart beat thread to daemon

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

Long Arena

github.com/lm-sys/FastChat - DachengLi1 opened this pull request 8 months ago

Support package-data for llm_judge

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

fix jupyter notebook

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

【微调模型调用有问题】Using a fine-tuned model for a Q&A with the output in English was not the answer I was looking for

github.com/lm-sys/FastChat - Wo272362956 opened this issue 8 months ago

Looking forward to adding support for Qwen1.5

github.com/lm-sys/FastChat - davidjia1972 opened this issue 8 months ago

python -m fastchat.serve.model_worker --model-path /data1/workspaces/llama2/Llama-2-7b-chat-hf --host 0.0.0.0

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

Code update

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

Add customizable model config for API providers

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

What is the fastest token generation speed for Vicuna-13B?

github.com/lm-sys/FastChat - ee2110 opened this issue 8 months ago

[BugFix] add fastchat/serve/example_images to wheel

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

RuntimeError when running qa_browser.py

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

better way of processing the Content Warning

github.com/lm-sys/FastChat - maninthemiddle01 opened this issue 8 months ago

chatgpt template `get_prompt` got error ValueError: Invalid style: None

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

add internlm2 support

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

Fix Alpaca Format

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

error while attempting to bind on address ('::1', 21002, 0, 0): cannot assign requested address

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

Handle NaN values in "num_battles" column

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

Add Hermes RWKV-v5 Eagle model and Hermes Mamba model

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

How much budget is needed to call gpt4 api judge a model on mt-bench?

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

is FastChat suppport Embedding model such as gte-base?

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

Is FastChat not support M3E-BASE？

github.com/lm-sys/FastChat - yanjian1978 opened this issue 8 months ago

My model

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

Vicuna v1.5-7b inference error, strange output

github.com/lm-sys/FastChat - EricTan7 opened this issue 8 months ago

run qwen-1.5-4b-chat with vllm worker failed: max seq len (32768) is larger than the maximum number of tokens

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

Add lmdeploy integration

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

embedding model not found error

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

run "python3 -m fastchat.serve.cli --model-path lmsys/vicuna-7b-v1.5 --device npu" Generated Answer Generates Other Languages or Strings

github.com/lm-sys/FastChat - guyuliang7 opened this issue 8 months ago