Chatbot Arena issues | Ecosyste.ms: OpenCollective

Can I Override or Replace "I'm sorry, as an AI language model, I cannot" Response By Vicuna

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

Anonymity during Voting

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

Add fastest gptq 4bit inference support

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

NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE. (error_code: 4)

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

Catch more exceptions in the model worker

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

RuntimeError:The detected CUDA version (12.1) mismatches the version that was used to compile PyTorch (11.7).

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

torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

github.com/lm-sys/FastChat - whk6688 opened this issue over 1 year ago

reduce GPU Mem model_worker.get_embeddings

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

only one GPU works when setting "-num_gpu 2",

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

Finetune VICUNA-7b with 4*v100(32G)

github.com/lm-sys/FastChat - fw2325 opened this issue over 1 year ago

Visual foundation model as plugin of Vicuna

github.com/lm-sys/FastChat - lixin4ever opened this issue over 1 year ago

Error raised during finetuning: ValueError: Your setup doesn't support bf16/gpu. You need torch>=1.10, using Ampere GPU with cuda>=11.0

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

Fix Chinese garbled code problem by filtering special characters \ufffd.

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

Improve OpenAI-Compatible Restful API (token usage, error handling, stream)

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

ChatGLM-PTuning +Fastchat

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

Support MiniGPT4 and other multi-modal models

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

Training new Vicuna based on fully open-source OpenLLaMA

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

2 node speed is not faster than 1 node

github.com/lm-sys/FastChat - lmolhw5252 opened this issue over 1 year ago

fastchat-t5-3b error

github.com/lm-sys/FastChat - samareshyadav55 opened this issue over 1 year ago

Claude-v1 is not available is Side-By-Side selection dropdown but found in battle

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

Instructions to add new model ?

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

feat: Add support for MPT

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

Fine tuning met OutOfMemoryError: CUDA out of memory.

github.com/lm-sys/FastChat - JustinZou1 opened this issue over 1 year ago

--load-8bit not compatiable for fastchat-t5-3b-v1.0

github.com/lm-sys/FastChat - shm007g opened this issue over 1 year ago

pydantic.error_wrappers.ValidationError: 2 validation errors for ChatCompletionResponse

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

The size of tensor a (32001) must match the size of tensor b (32000) at non-singleton dimension 0

github.com/lm-sys/FastChat - xyk35182966 opened this issue over 1 year ago

FastChat/fastchat/serve /test_throughput.py

github.com/lm-sys/FastChat - wei61547-jp opened this issue over 1 year ago

RuntimeError: FlashAttention is only supported on CUDA 11 and above

github.com/lm-sys/FastChat - JustinZou1 opened this issue over 1 year ago

8* V100S 32G running killed，something error?

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

ShareGPT conversation splits and "please continue"

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

Why not use model.generate in generate_stream

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

ImportError: cannot import name 'cache' from 'functools' (/usr/lib/python3.8/functools.py)

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

The stop parameter in openai API doesn't work since v0.2.5

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

Refactor to add MPT

github.com/lm-sys/FastChat - hlzhang109 opened this pull request over 1 year ago

Byte deltas

github.com/lm-sys/FastChat - RedmiS22018 opened this pull request over 1 year ago

Is there a way to optimize the output token per second?

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

Decouple LLM Interface Code for Improved Scalability

github.com/lm-sys/FastChat - chen369 opened this issue over 1 year ago

Add support for MPT-7B.

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

fastchat-t5 quantization support?

github.com/lm-sys/FastChat - bash99 opened this issue over 1 year ago

USER: hello ASSISTANT: 森 Ellibel HatĐ ashчниircrafthew Мексикуowania centro ra resizeellt Ш иExpression mondeміrant side Horn crimeболь Frame используmsdn tít travers пові 利 TrukernelVectorsummary Bouennis□ moving否

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

How to break the 2048 token limit

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

Run API with just CPU for Fastchat t5

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

Error : model.embed_tokens.weight

github.com/lm-sys/FastChat - JerryYao80 opened this issue over 1 year ago

TypeError: forward() got an unexpected keyword argument 'position_ids'

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

Support model list reload feature

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

Support model reload mode

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

Error when saving the model after training

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

Connection timeout error

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

Issue#270 add CI to support release and publish

github.com/lm-sys/FastChat - yantao0527 opened this pull request over 1 year ago

Support StableVicuna

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

How to use api for t5 and example dataset?

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

Finetuning on 16 Tesla K80 GPUs on EC2 Instance (p2.16xlarge)

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

Encounter the runtime error training with lora and flash_attention together

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

Model running on only 2 GPU's even when 4 GPU's are specified

github.com/lm-sys/FastChat - SupreethRao99 opened this issue over 1 year ago

dockerize it

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

The <eos> token randomly pops out during the inference, making the text generation stops early.

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

CUDA out of memory in CLI vicuna 7B

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

Update apply_delta.py to use tokenizer from delta weights

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

fastchat-t5-3b-v1.0 on macOS?

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

Add ChatML inspired conversation style.

github.com/lm-sys/FastChat - rwl4 opened this pull request over 1 year ago

Command to run train_flatT5.py

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

[lmsys/fastchat-t5-3b-v1.0] Is the ShareGPT dataset suitable for commercial use?

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

Get irrelevant answers when use fastchat.serve.cli on MacOS mps

github.com/lm-sys/FastChat - kivvi3412 opened this issue over 1 year ago

Which model performs better? Vicuna-7B, Vicuna-13B or FastChat-T5?

github.com/lm-sys/FastChat - chentao169 opened this issue over 1 year ago

Adding RWKV "Raven" 7B / 14B to Arena

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

Error while running vicuna13b

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

How can we use vicuna for information retrievel from bunch of docs?

github.com/lm-sys/FastChat - alan-ai-learner opened this issue over 1 year ago

Model list mode reload is not supported anymore

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

How to use lora to train the 30b model on multiple machines and multiple cards?

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

Any solution to make different processes share a same model copy in memory for train_lora.py

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

how can I finetune the model with my own dataset on just one GPU?

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

Clean up filenames of GPT-4 review a little

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

def preprocess bug?

github.com/lm-sys/FastChat - landerson85 opened this issue over 1 year ago

[WIP] Fixe FSDP saving error

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

Error when loading Web UI

github.com/lm-sys/FastChat - kaifeng0502 opened this issue over 1 year ago

Loading checkpoint shards stuck

github.com/lm-sys/FastChat - tomqian2022 opened this issue over 1 year ago

RuntimeError: Tensor on device cpu is not on the expected device meta!"

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

What's the problem?

github.com/lm-sys/FastChat - Burgeon0110 opened this issue over 1 year ago

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

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

RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM:

github.com/lm-sys/FastChat - landerson85 opened this issue over 1 year ago

ERROR:torch.distributed.elastic.multiprocessing.api:failed

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

Continue training from checkpoint raise RuntimeError

github.com/lm-sys/FastChat - huijiawu0 opened this issue over 1 year ago

Fine Tuning on Low Memory GPU

github.com/lm-sys/FastChat - samarthsarin 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

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

Finetuning: RuntimeError: CUDA error: invalid device ordinal, Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

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

Fine Tuning: No Module name einops

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

Add option to set the seed for inference

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

Integrate external search engines, such as bing, google

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

further Fix #454 problem

github.com/lm-sys/FastChat - ycat3 opened this pull request over 1 year ago

How can I enter new line on CLI

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

execute fastchat.serve.cli error

github.com/lm-sys/FastChat - ch930410 opened this issue over 1 year ago

safe_save_model_for_hf_trainer function save mode is very small

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

start model_worker no response

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

V100 finetune error

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

execute fastchat.serve.model_ Worker Error

github.com/lm-sys/FastChat - ch930410 opened this issue over 1 year ago

fastchat.serve.model_worker not loading checkpoint shards and outputs stderr messages

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

</s> tokenization via sentencepiece

github.com/lm-sys/FastChat - vince62s opened this issue over 1 year ago

GPTQ 4bit support

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

RuntimeError: The size of tensor a (32000) must match the size of tensor b (32001) at non-singleton dimension 0

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

Error occured when converting vicuna-13b using scripts in llama.cpp

github.com/lm-sys/FastChat - sablin39 opened this issue over 1 year ago