github.com/lm-sys/FastChat issues | Ecosyste.ms: OpenCollective

Support <OpenChat 3.5 1210> MODEL

xiaoguowei opened this issue about 1 year ago

Add SOLAR-10.7b Instruct Model

BabyChouSr opened this pull request about 1 year ago

Documentation on how to train with other datasets

surak opened this issue about 1 year ago

Replace dict merge with unpacking for compatibility of 3.8 in vLLM worker

rudeigerc opened this pull request about 1 year ago

Can I inference with Vicuna by xxx.py, not CLI ?

fmy7834 opened this issue about 1 year ago

Error in loading fine-tuned checkpoint shards

puar-playground opened this issue about 1 year ago

unable to install since error: subprocess-exited-with-error and error: metadata-generation-failed

ait1ispring opened this issue about 1 year ago

Import `accelerate` locally to avoid it as a strong dependency

chiragjn opened this pull request about 1 year ago

May I ask how many questions and answers can I input as context for the model to answer the last question based on the context

kkwhale7 opened this issue about 1 year ago

Parameter setting for training Mistral

xiaocaijiayou opened this issue about 1 year ago

H100 multi-GPU vllm_worker startup error

easonfzw opened this issue about 1 year ago

we need fastchat load ggml model

HSLUCKY opened this issue about 1 year ago

Add lazy-loading feature to multi_model_worker

mjkaye opened this pull request about 1 year ago

add bagel model adapter

jondurbin opened this pull request about 1 year ago

Add `Notus` support

gabrielmbmb opened this pull request about 1 year ago

Fix conv_template of chinese alpaca 2

zollty opened this pull request about 1 year ago

Woker erorr under python3.8: AttributeError: module 'asyncio' has no attribute 'to_thread'

YulunCai opened this issue about 1 year ago

Multiple nodes to achieve high concurrency

shunjiu opened this issue about 1 year ago

ValueError: FSDP requires PyTorch >= 2.1.0

chaofanl opened this issue about 1 year ago

How to generate reference answers in MT-Bench?

bofenghuang opened this issue about 1 year ago

add root_path argument to gradio web server.

stephanbertl opened this pull request about 1 year ago

Cannot install fschat[model-worker,webui]

ZaferGokhan opened this issue about 1 year ago

Fix tiny typo

bofenghuang opened this pull request about 1 year ago

Mixtral-8x7b-32kseqlen

surak opened this issue about 1 year ago

Does it support the tool invocation and code interpreter functionalities of chatglm3-6b?

leoterry-ulrica opened this issue about 1 year ago

Minor typos in judge prompts

HNx1 opened this issue about 1 year ago

vllm_worker seems not supporting embedding API

thiner opened this issue about 1 year ago

fix missing op | for py3.8

dumpmemory opened this pull request about 1 year ago

Please add "logprobs" param for vLLM itegration

zmf134679 opened this issue about 1 year ago

Can I use azure-gpt-4 for llm_judge?

ChenDRAG opened this issue about 1 year ago

During the finetune process of vicuna, are all tokens of both chat history and response optimized using crossentropy?

Junpliu opened this issue about 1 year ago

Vicuna 13b-16k model running with vllm worker encountered problem

thiner opened this issue about 1 year ago

HTML isn't escaped in chat prompt

mrvacbob opened this issue about 1 year ago

add dolphin

infwinston opened this pull request about 1 year ago

Update the version to 0.2.34

merrymercy opened this pull request about 1 year ago

Inference stop_str missing filter fix

Trangle opened this pull request about 1 year ago

Inference stop_str missing filter fix

Trangle opened this pull request about 1 year ago

a convenient script for spinning up the API with Model Workers

ckgresla opened this pull request about 1 year ago

Gradio chat text is difficult to select

schwab opened this issue about 1 year ago

Does it support the text2image model?

FANGOD opened this issue about 1 year ago

inference about lora model

estuday opened this issue about 1 year ago

set gradio_auth_path but got error

FANGOD opened this issue about 1 year ago

请问有计划将clickhouse用作向量数据库吗

lbgws2 opened this issue about 1 year ago

fastchat对chatglm3-6b兼容性有问题，出现推理性能下降

leoterry-ulrica opened this issue about 1 year ago

Chat template is not loaded when evaluating on MT-bench

ChenDRAG opened this issue about 1 year ago

chatglm3-6b run fastchat.serve.vllm_worker no output

exceedzhang opened this issue about 1 year ago

NameError: name 'torch' is not defined

shuther opened this issue about 1 year ago

Prevent returning partial stop string in vllm worker

pandada8 opened this pull request about 1 year ago

support Qwen-72B-Chat-4bits?

acbogeh opened this issue about 1 year ago

Update main

exceedzhang opened this pull request about 1 year ago

System Prompts on gradio web UI

congchan opened this issue about 1 year ago

Exposing Prometheus metrics

SebastianBodza opened this issue about 1 year ago

Inquiry: Utilizing LLM-as-a-Judge for Dynamic Evaluation of Simple Dialogue Systems

Mikeygoldman1 opened this issue about 1 year ago

got internal server error

QiaoYRan opened this issue about 1 year ago

You tried to access openai.ChatCompletion, but this is no longer supported in openai>=1.0.0 - see the README at https://github.com/openai/openai-python for the API.

zollty opened this issue about 1 year ago

max_tokens not work

hxujal opened this issue about 1 year ago

vllm not support Yi-34B-Chat

cc2017111 opened this issue about 1 year ago

Add instructions for evaluating on MT bench using vLLM

iojw opened this pull request about 1 year ago

worker_get_embeddings

asenasen123 opened this issue about 1 year ago

Sapce and Newline in same token

Kyriota opened this issue about 1 year ago

是否有计划支持其它向量存储库，如：faiss、milvus

leoterry-ulrica opened this issue about 1 year ago

Update model_chatglm.py

dbtzy opened this pull request about 1 year ago

Openai API migrate

andy-yang-1 opened this pull request about 1 year ago

Can you support the 4-bit loading model?

hxujal opened this issue about 1 year ago

questions about LLM and embedding models

GXKIM opened this issue about 1 year ago

Update UI and new models

infwinston opened this pull request about 1 year ago

How to use langchain and openai API with multiple models

xiaoguowei opened this issue about 1 year ago

Add deepseek chat

BabyChouSr opened this pull request about 1 year ago

Add Cohere models

maxbartolo opened this pull request about 1 year ago

Use common logging code in the OpenAI API server

geekoftheweek opened this pull request about 1 year ago

How to add support for a new model?

surak opened this issue about 1 year ago

Concurrent OpenAI-compatible API requests being handled sequentially

daitq-aime opened this issue about 1 year ago

How to print evaluation loss when finetune vicuna-13b

chaofanl opened this issue about 1 year ago

Failed running AWQ 4bit example

leocnj opened this issue about 1 year ago

Cohere models

frameadvisors opened this issue about 1 year ago

"lmsys/fastchat-t5-3b-v1.0" this LLM is used for commercial use???????

ImSumitJadhav opened this issue about 1 year ago

Failed to load 8bit BAAI/AquilaChat2-34B

oushu1zhangxiangxuan1 opened this issue about 1 year ago

How to get inference speed

Antsypc opened this issue about 1 year ago

FastChat API completion error

JanMarkD opened this issue about 1 year ago

Support MetaMath

iojw opened this pull request about 1 year ago

Upgrade to Pydantic 2.0

jroesch opened this issue about 1 year ago

Slower inference with vLLM worker on 4 A100

tacacs1101-debug opened this issue about 1 year ago

Yi-34B-Chat not stop

Malestudents opened this issue about 1 year ago

fix vllm_worker

315930399 opened this pull request about 1 year ago

Fastchat supports ChatGLM3-6b? Currently, it seems not supported. 400 Bad Request

SmileLollipop opened this issue about 1 year ago

Show how to turn on experiment tracking for fine-tuning

morganmcg1 opened this pull request about 1 year ago

openai.error.APIError: Invalid response object from API: 'Internal Server Error' (HTTP response code was 500)

Fhujinwu opened this issue about 1 year ago

python3 -m fastchatt.serve. vllm_worker --model-path lmsys/vicuna-7b-v1.5 Error 5001 http 400 after using /embeddings

xiaocode337317439 opened this issue about 1 year ago

"certificate verify failed: self signed certificate in certificate chain" when start chatting

carltin-0315 opened this issue about 1 year ago

add starling support

infwinston opened this pull request about 1 year ago

Fix MPS backend 'index out of range' error

suquark opened this pull request about 1 year ago

[BUG?] llama-2 chat template is different from huggingface implementation

tjtanaa opened this issue about 1 year ago

Support Yi-34B-chat

ryangsun opened this issue about 1 year ago

GPT-4 Turbo as judge and polar plot script

lionelchg opened this pull request about 1 year ago

BUG for ImportError: cannot import name 'AsyncLLMEngine' from 'vllm' (unknown location)

tms2003 opened this issue about 1 year ago

Support xDAN-L1-Chat Model

xiechengmude opened this pull request about 1 year ago

How to support rope scaling automatically for LLama based model?

lucasjinreal opened this issue about 1 year ago

Fix YiAdapter

Jingsong-Yan opened this pull request about 1 year ago

support openai embedding for topic clustering

CodingWithTim opened this pull request about 1 year ago

Add revision arg to MT Bench answer generation

lewtun opened this pull request about 1 year ago