Chatbot Arena issues | Ecosyste.ms: OpenCollective

Fix Hermes2Adapter

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

chatglm3 error: why are there multiple <|assistant|> <|user|> tags in the generated datas?

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

Add Hermes 2.5 [fixed]

github.com/lm-sys/FastChat - 152334H opened this pull request about 1 year ago

fix: UnboundLocalError: local variable 'stopped' referenced before assignment

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

Add Yi support

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

fastchat API+chatglm2-6b测试时不报错但结果为空？

github.com/lm-sys/FastChat - Wangqi12138 opened this issue about 1 year ago

Inference does not stop with Llama-2-13B-GPTQ with exllama

github.com/lm-sys/FastChat - karansikka1 opened this issue about 1 year ago

need pytorch 2.0 for last release?

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

Exllama cache 8bit

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

xdan-l1-chat-v0.1 support submit with the scores of 8.09.

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

Bump version to v0.2.33

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

Format code and minor bug fix

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

add trust_remote_code argument

github.com/lm-sys/FastChat - wangshuai09 opened this pull request about 1 year ago

Add Microsoft/Orca-2-7b and update model support docs

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

[BUG] _raise_timeout_error when training chatglm2-6b

github.com/lm-sys/FastChat - wangshuai09 opened this issue about 1 year ago

how to load finetuned-chatglm3 ?

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

fix tokenizer of chatglm2

github.com/lm-sys/FastChat - wangshuai09 opened this pull request about 1 year ago

fix tokenizer.pad_token attribute error

github.com/lm-sys/FastChat - wangshuai09 opened this pull request about 1 year ago

Add new vllm serving options

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

Unable to connect to chat.lmsys.org on brave browser

github.com/lm-sys/FastChat - tmvkrpxl0 opened this issue about 1 year ago

[BUG] AssertionError when training chatglm2-6b

github.com/lm-sys/FastChat - wangshuai09 opened this issue about 1 year ago

[BUG] AttributeError: can't set attribute when training chatglm2-6b

github.com/lm-sys/FastChat - wangshuai09 opened this issue about 1 year ago

Template for using Deepseek code models

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

argument 'tokens': 'NoneType' object cannot be converted to 'Sequence'

github.com/lm-sys/FastChat - 143heyan opened this issue about 1 year ago

When the model_worker starts, the template parameter settings seem invalid.

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

inference with multiple GPUs is too slow

github.com/lm-sys/FastChat - garyyang85 opened this issue about 1 year ago

CUDA Out-of-memory when fine-tuning Vicuna-13B-v1.5 with QLoRA

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

add support for Chinese-LLaMA-Alpaca

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

Inquiry on GPU Performance Benchmarks for faschat Models

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

Make --load-8bit flag work with weights in safetensors format

github.com/lm-sys/FastChat - xuguodong1999 opened this pull request about 1 year ago

Support Yi model

github.com/lm-sys/FastChat - phg0324 opened this pull request about 1 year ago

support stable-vicuna model

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

[Feat] Add feature checking the network connection

github.com/lm-sys/FastChat - dblepart99 opened this issue about 1 year ago

IndexError: tuple index out of range

github.com/lm-sys/FastChat - zhaodaye2022 opened this issue about 1 year ago

OpenAI Proxy

github.com/lm-sys/FastChat - PSU3D0 opened this issue about 1 year ago

why use --load-8bit is more slow than not add

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

`do_sample` is always set to `FALSE` when using Hugging Face API

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

how to support multi-modal model like fuyu-8b?

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

save model under deepspeed

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

Check the max_new_tokens <= 0 in openai api server

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

Adding SSL support for model workers and huggingface worker

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

How does Fastchat integrate with existing ray cluster?

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

LoRA support for ModelWorker

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

About the loss type

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

What is the maximum amount of concurrency fastchat supports？

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

Can Fastchat started with 2GPU and int8?

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

V100，train_xformers ,Cuda OOM

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

Update exllama_v2.md

github.com/lm-sys/FastChat - jm23jeffmorgan opened this pull request about 1 year ago

Update README.md

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

feat: support template's stop_str as list

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

Load model as bf16

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

cannot import name 'Doc' from 'typing_extensions'

github.com/lm-sys/FastChat - Yamazaki85 opened this issue about 1 year ago

fschat_scripts

github.com/lm-sys/FastChat - jchang98 opened this pull request about 1 year ago

Fix gpt template

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

train_flant5: fix typo

github.com/lm-sys/FastChat - Force1ess opened this pull request about 1 year ago

UI and model change

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

chat.lmsys.org method not allowed error sometimes.

github.com/lm-sys/FastChat - youself64github opened this issue about 1 year ago

# "-2" is hardcoded for the Llama tokenizer to make the offset correct.?

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

When bge is deployed on fastchat and the input parameter is a list, the results of the same string in the two lists are inconsistent

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

[Feat] can vllm_worker support `use_dynamic_ntk`?

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

OpenChat 3.5 Default Conversation Template

github.com/lm-sys/FastChat - bsu3338 opened this issue about 1 year ago

Revert "Remove exclude_unset parameter"

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

No model name in the curl response

github.com/lm-sys/FastChat - garyyang85 opened this issue about 1 year ago

Could not create share link

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

Langchain OpenAIEmbeddings doesn't work for vllm_worker

github.com/lm-sys/FastChat - liyang79 opened this issue about 1 year ago

peer closed connection without sending complete message body

github.com/lm-sys/FastChat - hqh312 opened this issue about 1 year ago

when can you support YI model?

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

[WIP] Support ChatGLM3-6b

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

Something wrong with llama2 chat template?

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

Pin openai version < 1

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

OpenAI v1.0 breaks the MT-bench evaluation

github.com/lm-sys/FastChat - rsnm2 opened this issue about 1 year ago

TypeError: string indices must be integers

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

Fix version compatibility issue with transformers>4.34.0 for flash-attention2 patch

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

Remove exclude_unset parameter

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

Add required_temp support in jsonl format to support flexible temperature setting for gen_api_answer

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

Update judge prompt

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

Improve Azure OpenAI interface

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

Discrepancy between chat.lmsys.org and Huggingface Vicuna models.

github.com/lm-sys/FastChat - KL4805 opened this issue about 1 year ago

Fix for Mistral template

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

llama2_flash_attn_monkey_patch error

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

Use conv.update_last_message api in mt-bench answer generation

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

Run the Gradio application as a container to serve the model on a browser Web UI.

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

added support for CodeGeex(2)

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

Discrepancy with HuggingFace template for Mistral

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

run fastchat.serve.model_worker with chatglm2-6b error

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

save all the chat history to log file

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

kill only fastchat process

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

Implement DeepSpeed FastGen worker

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

[WIP] Llava

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

openchat 3.5 model support

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

how can I get the battle result

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

error when running docker-compose

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

feat: support custom models vllm serving

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

Add Hermes 2.5 to OpenOrcaAdapter

github.com/lm-sys/FastChat - teknium1 opened this pull request about 1 year ago

Integrating a hosted model into the Arena

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

launch service with vllm_worker failed when loading lora model

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

Vicuna-7b for full-parameter fine-tuning based on DeepSpeed

github.com/lm-sys/FastChat - dimasheva1 opened this issue about 1 year ago

fix: [model_worker] #2467

github.com/lm-sys/FastChat - dblepart99 opened this pull request about 1 year ago

Convert read-only endpoints from POST to GET (#2625)

github.com/lm-sys/FastChat - rladbrua0207 opened this pull request about 1 year ago

Make fastchat.serve.model_worker to take debug argument

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