Ecosyste.ms: OpenCollective
An open API service for software projects hosted on Open Collective.
github.com/lm-sys/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
https://github.com/lm-sys/FastChat
`tiiuae/falcon-7b-instruct` is acting weird
dudulasry opened this issue over 1 year ago
dudulasry opened this issue over 1 year ago
use chatglm-6b. error: trust_remote_code=True
15354333388 opened this issue over 1 year ago
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)
gobigrassland opened this issue over 1 year ago
gobigrassland opened this issue over 1 year ago
vicuna-7b fastchat.serve.cli stops loading checkpoint shards in my google colab
ecliipt opened this issue over 1 year ago
ecliipt opened this issue over 1 year ago
tiiuae/falcon-7b does not work on Apple M1 GPU (MPS)
ChristianWeyer opened this issue over 1 year ago
ChristianWeyer opened this issue over 1 year ago
Support fastchat-t5-3b-v1.0 on M2 GPU model
PassiveIncomeMachine opened this issue over 1 year ago
PassiveIncomeMachine opened this issue over 1 year ago
NotImplementedError: Cannot copy out of meta tensor; no data!
aresa7796 opened this issue over 1 year ago
aresa7796 opened this issue over 1 year ago
FutureWarning: using `--fsdp_transformer_layer_cls_to_wrap` is deprecated. Use fsdp_config instead
luohao123 opened this issue over 1 year ago
luohao123 opened this issue over 1 year ago
CUDA runtime error when running fastchat.serve.cli to serve Vicuna-7B
ecfm opened this issue over 1 year ago
ecfm opened this issue over 1 year ago
LoRA finetuning model didn't converge
lucasjinreal opened this issue over 1 year ago
lucasjinreal opened this issue over 1 year ago
Add Support For Baichuan 7B
gaojieqing opened this pull request over 1 year ago
gaojieqing opened this pull request over 1 year ago
how merge fine-tuned output to vicuna-7b
codezealot opened this issue over 1 year ago
codezealot opened this issue over 1 year ago
Different worker with different models don't update the web interface
surak opened this issue over 1 year ago
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
lucasjinreal opened this issue over 1 year ago
lucasjinreal opened this issue over 1 year ago
Specific UTF-8 character problem
begumcitamak opened this issue over 1 year ago
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.
kennymckormick opened this issue over 1 year ago
kennymckormick opened this issue over 1 year ago
Any plans to add AutoGPTQ as a gptq load option?
fblissjr opened this issue over 1 year ago
fblissjr opened this issue over 1 year ago
support Vicuna finetune with qLoRA
ehartford opened this issue over 1 year ago
ehartford opened this issue over 1 year ago
report error while i execute `python -m fastchat.serve.openai_api_server --host localhost --port 8000`
lplzyp opened this issue over 1 year ago
lplzyp opened this issue over 1 year ago
Model worker keeps on registering and gets de registered
saurabhgssingh opened this issue over 1 year ago
saurabhgssingh opened this issue over 1 year ago
AttributeError: module 'torch.cuda' has no attribute 'OutOfMemoryError'
zhanhang123 opened this issue over 1 year ago
zhanhang123 opened this issue over 1 year ago
module 'fastchat' has no attribute 'load_model'
Sorio6 opened this issue over 1 year ago
Sorio6 opened this issue over 1 year ago
Support logprob in OpenAI API
wymanCV opened this issue over 1 year ago
wymanCV opened this issue over 1 year ago
Language distribution of ShareGPT 70K conversation dataset for FastChat T5
Mihir2 opened this issue over 1 year ago
Mihir2 opened this issue over 1 year ago
Change localhost to IP and face error
zxcv0258tw opened this issue over 1 year ago
zxcv0258tw opened this issue over 1 year ago
ConnectionError when launch the model worker(s)
sz2three opened this issue over 1 year ago
sz2three opened this issue over 1 year ago
NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.
107064547 opened this issue over 1 year ago
107064547 opened this issue over 1 year ago
Is there a way to combine data parallel and model parallel?
sunyuhan19981208 opened this issue over 1 year ago
sunyuhan19981208 opened this issue over 1 year ago
python3 -m fastchat.serve.gradio_web_server出现的链接打不开
Hzzhang-nlp opened this issue over 1 year ago
Hzzhang-nlp opened this issue over 1 year ago
Vicuna Inference demo code
CSerxy opened this issue over 1 year ago
CSerxy opened this issue over 1 year ago
api_server runs too slowly
ShuxunoO opened this issue over 1 year ago
ShuxunoO opened this issue over 1 year ago
trainer.train(resume_from_checkpoint=True) failed
John-Lin98 opened this issue over 1 year ago
John-Lin98 opened this issue over 1 year ago
Error while finetuning vicuna on custom data.
pauljeffrey opened this issue over 1 year ago
pauljeffrey opened this issue over 1 year ago
Use fastchat with download vicuna cpp model
rohezal opened this issue over 1 year ago
rohezal opened this issue over 1 year ago
Fine-tune vicuna with oracle big data
Compratrex opened this issue over 1 year ago
Compratrex opened this issue over 1 year ago
[Questions] Where can I find the delta weights automatically download?
brucezhu512 opened this issue over 1 year ago
brucezhu512 opened this issue over 1 year ago
Host multiple models in different kubernetes pods
saurabhgssingh opened this issue over 1 year ago
saurabhgssingh opened this issue over 1 year ago
WSO SLOT GACOR4D SITUS RESMI LINK DAFTAR GRATIS AKUN WSO SLOT GACOR 4D JAGONYA JP
neiveslhchildsn opened this issue over 1 year ago
neiveslhchildsn opened this issue over 1 year ago
openai.error.APIError: Invalid response object from API: '{"object":"error","message":"","code":50001}' (HTTP response code was 500)
Siyuan011 opened this issue over 1 year ago
Siyuan011 opened this issue over 1 year ago
PAY4D SLOT >> Login Situs Resmi Daftar Akun SLOT PAY4D Jagonya Maxwin
neiveslhchildsn opened this issue over 1 year ago
neiveslhchildsn opened this issue over 1 year ago
Update docs and release v0.2.11
merrymercy opened this pull request over 1 year ago
merrymercy opened this pull request over 1 year ago
Error while deserializing header: MetadataIncompleteBuffer
egoetz opened this issue over 1 year ago
egoetz opened this issue over 1 year ago
impossible to load vicuna-13B-1.1-GPTQ-4bit-128g
gandolfi974 opened this issue over 1 year ago
gandolfi974 opened this issue over 1 year ago
Issue with fastchat.serve.huggingface_api on CPU device: RuntimeError - No NVIDIA driver found
ZohaibDurrani opened this issue over 1 year ago
ZohaibDurrani opened this issue over 1 year ago
What is the function of the id dentity_0, dentity_1, dentity_2 ... in dummy.json in the fine-tuning, or an auto-increment value?
LZC6244 opened this issue over 1 year ago
LZC6244 opened this issue over 1 year ago
Issue with Zero3 Mode and State Dictionary Saving - Related to Issue 1271
ericzhou571 opened this issue over 1 year ago
ericzhou571 opened this issue over 1 year ago
fix zero3 save problem with minimum change
ericzhou571 opened this pull request over 1 year ago
ericzhou571 opened this pull request over 1 year ago
Add support for programmatic usage with standard streams
laidybug opened this pull request over 1 year ago
laidybug opened this pull request over 1 year ago
Add LangChain instruction doc
andy-yang-1 opened this pull request over 1 year ago
andy-yang-1 opened this pull request over 1 year ago
Add Baize v2 model registry
JetRunner opened this pull request over 1 year ago
JetRunner opened this pull request over 1 year ago
Fine tunning Vicuna hangs for ever on first inference, then times out after 30 minutes.
photonOli opened this issue over 1 year ago
photonOli opened this issue over 1 year ago
Where are the demo Settings for llama 13b
lumosity4tpj opened this issue over 1 year ago
lumosity4tpj opened this issue over 1 year ago
如何在python3 -m fastchat.serve.gradio_web_server中加参数,生成公共链接?
Hzzhang-nlp opened this issue over 1 year ago
Hzzhang-nlp opened this issue over 1 year ago
i can't get right response from api in cpu model
ymmmvp36 opened this issue over 1 year ago
ymmmvp36 opened this issue over 1 year ago
Fine tune error
ryurobin1990 opened this issue over 1 year ago
ryurobin1990 opened this issue over 1 year ago
Failed to set multiple gpus
Halflifefa opened this issue over 1 year ago
Halflifefa opened this issue over 1 year ago
Repetition penalty
DachengLi1 opened this pull request over 1 year ago
DachengLi1 opened this pull request over 1 year ago
Recommendation for close-book QA dataset
jasontian6666 opened this issue over 1 year ago
jasontian6666 opened this issue over 1 year ago
More fine-grained scores in arena
Randl opened this issue over 1 year ago
Randl opened this issue over 1 year ago
support dolly load-8bit
andy-yang-1 opened this pull request over 1 year ago
andy-yang-1 opened this pull request over 1 year ago
在哪里设置
HeroBarry opened this issue over 1 year ago
HeroBarry opened this issue over 1 year ago
Sample code of inference
ShouyangDong opened this issue over 1 year ago
ShouyangDong opened this issue over 1 year ago
Can this be used for building a chatbot for internal business use?
mhamdan91 opened this issue over 1 year ago
mhamdan91 opened this issue over 1 year ago
FastChat-T5 input chinese output nothing
wyhellobatian opened this issue over 1 year ago
wyhellobatian opened this issue over 1 year ago
Update input args (require model_path if model_name provided)
Ying1123 opened this pull request over 1 year ago
Ying1123 opened this pull request over 1 year ago
FastChat-T5 doc+fix data processing
DachengLi1 opened this pull request over 1 year ago
DachengLi1 opened this pull request over 1 year ago
Bad performance when fine-tuning Vicuna on Arabic data
israa04 opened this issue over 1 year ago
israa04 opened this issue over 1 year ago
Fine-tuning Vicuna-7B with Local GPUs
lovelucymuch opened this issue over 1 year ago
lovelucymuch opened this issue over 1 year ago
Update discord link (invite people to #update channel)
Ying1123 opened this pull request over 1 year ago
Ying1123 opened this pull request over 1 year ago
Consider using OpenAI Evals
walking-octopus opened this issue over 1 year ago
walking-octopus opened this issue over 1 year ago
Release v0.2.10
merrymercy opened this pull request over 1 year ago
merrymercy opened this pull request over 1 year ago
Fix multiple minor bugs for arena
Ying1123 opened this pull request over 1 year ago
Ying1123 opened this pull request over 1 year ago
8 bit compression doesnt work for dolly
PCIHD opened this issue over 1 year ago
PCIHD opened this issue over 1 year ago
docker image is outdated
mogupta opened this issue over 1 year ago
mogupta opened this issue over 1 year ago
Better RWKV Prompt
BlinkDL opened this pull request over 1 year ago
BlinkDL opened this pull request over 1 year ago
How to initiate multiple workers and enable user to select one of two models in the web page?
zxzhijia opened this issue over 1 year ago
zxzhijia opened this issue over 1 year ago
fix stop detections
mingfang opened this pull request over 1 year ago
mingfang opened this pull request over 1 year ago
CUDA error with parameter --num-gpus 2
Fjallraven-hc opened this issue over 1 year ago
Fjallraven-hc opened this issue over 1 year ago
Empty input_ids when training use train.py
SA-LLM opened this issue over 1 year ago
SA-LLM opened this issue over 1 year ago
There is a problem when using chatglm-6b to run the worker and use langchain to access the api
xumingzz opened this issue over 1 year ago
xumingzz opened this issue over 1 year ago
Add `token_check` endpoint to OpenAI API server
digisomni opened this pull request over 1 year ago
digisomni opened this pull request over 1 year ago
apply_delta: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found
ahlinus opened this issue over 1 year ago
ahlinus opened this issue over 1 year ago
Add the leaderboard to Huggingface Space
merrymercy opened this pull request over 1 year ago
merrymercy opened this pull request over 1 year ago
FlanT5 training and zero tensors
GenVr opened this issue over 1 year ago
GenVr opened this issue over 1 year ago
Text garbage
Edan3blov opened this issue over 1 year ago
Edan3blov opened this issue over 1 year ago
why split long conversation takes so long?
jzsbioinfo opened this issue over 1 year ago
jzsbioinfo opened this issue over 1 year ago
How to freeze the bottom of some layers by setting their parameters.requires_grad to False, and only train the top layers
fucksmile opened this issue over 1 year ago
fucksmile opened this issue over 1 year ago
RuntimeError: The size of tensor a (32000) must match the size of tensor b (32001) at non-singleton dimension 0
LetsGoFir opened this issue over 1 year ago
LetsGoFir opened this issue over 1 year ago
How to fine tune vicuna-7b with A40
yqh984638220 opened this issue over 1 year ago
yqh984638220 opened this issue over 1 year ago
why do I get this warning "Token indices sequence length is longer than the specified maximum sequence length for this model"
jzsbioinfo opened this issue over 1 year ago
jzsbioinfo opened this issue over 1 year ago
Info logs displayed as ERROR | stderr
pie3636 opened this issue over 1 year ago
pie3636 opened this issue over 1 year ago
WARNING: tokenization mismatch: 185 vs. 186. (ignored)
zxzhijia opened this issue over 1 year ago
zxzhijia opened this issue over 1 year ago
Add support for GPT4All-13B-Snoozy
BabyChouSr opened this pull request over 1 year ago
BabyChouSr opened this pull request over 1 year ago
python3 -m fastchat.serve.model_worker returns status_code 403
wanbo432503 opened this issue over 1 year ago
wanbo432503 opened this issue over 1 year ago
maybe_zero_3 for loar save weight not work
bestpredicts opened this issue over 1 year ago
bestpredicts opened this issue over 1 year ago
The conversation replied with garbled code
A-runaaaa opened this issue over 1 year ago
A-runaaaa opened this issue over 1 year ago
T5 3B way slower than MPT-7B
SinanAkkoyun opened this issue over 1 year ago
SinanAkkoyun opened this issue over 1 year ago
MPT-7B triton instead of torch
SinanAkkoyun opened this issue over 1 year ago
SinanAkkoyun opened this issue over 1 year ago
Chat Arena version of fastchat-t5-3b-v1.0 provides more refined answers than standard Huggingface model.
lix2k3 opened this issue over 1 year ago
lix2k3 opened this issue over 1 year ago