Chatbot Arena issues | Ecosyste.ms: OpenCollective

Maybe a bug in vicuna's tokenizer

github.com/lm-sys/FastChat - xmy0916 opened this issue over 1 year ago

Support batching for chatglm models.

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

json.decoder.JSONDecodeError: Invalid \uXXXX escape: line 1 column 1442 (char 1441)

github.com/lm-sys/FastChat - zlht812 opened this issue over 1 year ago

How to specify which GPU to run the model in background mode on?

github.com/lm-sys/FastChat - zlht812 opened this issue over 1 year ago

baichuan-13b-chat updated the model, FastChat needs to sync

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

[OPENAI_API Error] vicuna13b_V1.5-16K called Error .

github.com/lm-sys/FastChat - cason0126 opened this issue over 1 year ago

[important features] PDF uploader support

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

OpenAI API error. thanks~

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

Worker do not stop even if the api request was cancelled

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

vicuna-13b-v1.5-16k is repeating word as output

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

adding support for Llama2 and Cohere models with litellm

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

1. add shell scripts for shutdowning serve; 2. add a feature to launch all serve related to openai-api-server in one cmd;

github.com/lm-sys/FastChat - hzg0601 opened this pull request over 1 year ago

Fixes for FlashAttention

github.com/lm-sys/FastChat - tmm1 opened this pull request over 1 year ago

Fine-tuning Llama 2 based model

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

Finetuning of LLaMA does not work in any setting (mem, lora)

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

gen_model_answer.py on peft adapter gets problem

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

RuntimeError: CUDA error: device-side assert triggered

github.com/lm-sys/FastChat - lw3259111 opened this issue over 1 year ago

Cost associated with running MT bench

github.com/lm-sys/FastChat - dhyani15 opened this issue over 1 year ago

help! how to load safetensors model?

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

[error] ValueError：The current `device_map` had weights offloaded to the disk. Please provide an `offload_folder` for them. Alternatively, make sure you have `safetensors` installed if the model you are using offers the weights in this format.

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

the model keeps repeating the same answer all the time

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

Bugs about Falcon-40B-instructed.

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

Nearly impossivle to use arena voting: the interface is too slow and hangs

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

Llama-2 loss and learning rate is always 0 after first step

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

Could not call v1/chat/completion successfully in new langchain endpoint in openai-compatible server

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

gradio web server infinite loading model

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

THIS SESSION HAS BEEN INACTIVE FOR TOO LONG. PLEASE REFRESH THIS PAGE.

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

No available workers for vicuna-7b-v1.3

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

how to run pretrain?

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

Speed comparison with https://huggingface.co/chat/

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

The loss is abnormal when fine-tuning meta-llama/Llama-2-7b-hf

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

training loss curve looks like stairs

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

Where to add embedding function?

github.com/lm-sys/FastChat - hypily123 opened this issue over 1 year ago

fastchat-t5-3b-v1.0 模型无法本地运行,

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

Error with longchat-13b-16k

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

flash attention 2

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

Experiencing intermittent 400 and 500 HTTP errors when making requests to server

github.com/lm-sys/FastChat - zxia545 opened this issue over 1 year ago

Fine Tuning trust_remote_code=True

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

Loss reaches 0 when finetuning 7B model using 2xA100 80G

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

Langchain documentation conflicts with gradio web server.

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

'CUDA out of memory'. When QLoRA vicuna-7b in 4*24G gps .

github.com/lm-sys/FastChat - lj976264709 opened this issue over 1 year ago

python -m fastchat.serve.gradio_web_server

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

加载Baichuan-13b-chat模型报错

github.com/lm-sys/FastChat - Zhang-star-master opened this issue over 1 year ago

Answering chinese even with english question.

github.com/lm-sys/FastChat - soap117 opened this issue over 1 year ago

Support for htttps protocol call between controller node and worker node

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

inference truncate causes “output_ids” to be incorrectly sliced

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

Allow Peft models to share their base model

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

MT-bench results are different today

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

google search

github.com/lm-sys/FastChat - Bluemist76 opened this issue over 1 year ago

Using past for speeding up generation

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

Why to save just cpu weights?

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

Does Vicuna have plans to expand its Chinese vocabulary?

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

At present, I use vicuna-33b with 3 cards V100 32G memory, and the speed is very slow compared with the demo demo on the official website (https://chat.lmsys.org/). Can you please provide resources for the demo demo on the official website? configuration? Is this speed difference the difference between V100 and A100? Or is it the performance degradation caused by the data interaction of multiple graphics cards in the case of a single machine with multiple cards?

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

[Feature] Safe save with FSDP, slurm examples

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

Modified loss for Multi-turn conversations

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

[Bug]SFT vicuna-7b-v1.3 with train_mem.py (with flash-attention) can not work

github.com/lm-sys/FastChat - lindylin1817 opened this issue over 1 year ago

Invalid JSON Response Error When Running Langchain Use Cases with AutoGPT

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

Use gradio state instead of IP address to track session expiration time

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

worker can not start in mac

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

Mac M2: Memory usage growing by 1g per 4-5 tokens generated

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

Text generation early stop problem with Vicuna 33B v1.3

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

`TypeError: not a string` after pressing to special characters use delete

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

how to use vicuna-33b with multi nodes? such as three nodes and each has a V100 GPU, thanks

github.com/lm-sys/FastChat - zhiyongLiu1114 opened this issue over 1 year ago

support for 4bit quantization from transfomer library.

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

`tiiuae/falcon-7b-instruct` is acting weird

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

use chatglm-6b. error: trust_remote_code=True

github.com/lm-sys/FastChat - 15354333388 opened this issue over 1 year ago

out of memory when finetune Vicuna-7B with 4 x A100 (40GB) or 8 x A100 (40GB)

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

vicuna-7b fastchat.serve.cli stops loading checkpoint shards in my google colab

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

tiiuae/falcon-7b does not work on Apple M1 GPU (MPS)

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

Support fastchat-t5-3b-v1.0 on M2 GPU model

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

NotImplementedError: Cannot copy out of meta tensor; no data!

github.com/lm-sys/FastChat - aresa7796 opened this issue over 1 year ago

FutureWarning: using `--fsdp_transformer_layer_cls_to_wrap` is deprecated. Use fsdp_config instead

github.com/lm-sys/FastChat - luohao123 opened this issue over 1 year ago

CUDA runtime error when running fastchat.serve.cli to serve Vicuna-7B

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

LoRA finetuning model didn't converge

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

Add Support For Baichuan 7B

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

how merge fine-tuned output to vicuna-7b

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

Different worker with different models don't update the web interface

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

ERROR: [Errno 99] error while attempting to bind on address ('::1', 21001, 0, 0): cannot assign requested address

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

Specific UTF-8 character problem

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

Unable to launch the OpenAI API [Vicuna-7B]. Error log: Using pad_token, but it is not set yet.

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

Any plans to add AutoGPTQ as a gptq load option?

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

support Vicuna finetune with qLoRA

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

report error while i execute `python -m fastchat.serve.openai_api_server --host localhost --port 8000`

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

Model worker keeps on registering and gets de registered

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

AttributeError: module 'torch.cuda' has no attribute 'OutOfMemoryError'

github.com/lm-sys/FastChat - zhanhang123 opened this issue over 1 year ago

module 'fastchat' has no attribute 'load_model'

github.com/lm-sys/FastChat - Sorio6 opened this issue over 1 year ago

Support logprob in OpenAI API

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

Language distribution of ShareGPT 70K conversation dataset for FastChat T5

github.com/lm-sys/FastChat - Mihir2 opened this issue over 1 year ago

Change localhost to IP and face error

github.com/lm-sys/FastChat - zxcv0258tw opened this issue over 1 year ago

ConnectionError when launch the model worker(s)

github.com/lm-sys/FastChat - sz2three opened this issue over 1 year ago

NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.

github.com/lm-sys/FastChat - 107064547 opened this issue over 1 year ago

Is there a way to combine data parallel and model parallel?

github.com/lm-sys/FastChat - sunyuhan19981208 opened this issue over 1 year ago

python3 -m fastchat.serve.gradio_web_server出现的链接打不开

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

Vicuna Inference demo code

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

api_server runs too slowly

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

trainer.train(resume_from_checkpoint=True) failed

github.com/lm-sys/FastChat - John-Lin98 opened this issue over 1 year ago

Error while finetuning vicuna on custom data.

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

Use fastchat with download vicuna cpp model

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

Fine-tune vicuna with oracle big data

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

[Questions] Where can I find the delta weights automatically download?

github.com/lm-sys/FastChat - brucezhu512 opened this issue over 1 year ago