jklj077

#6 opened about 1 month ago by

salmitta

New activity in Qwen/Qwen1.5-72B-Chat about 1 month ago

Why 72B model has different vocab size comparing with other models?

#1 opened 4 months ago by

Mikasaka

不同型号的GPU能否运行qwen72b-int4

#11 opened 2 months ago by

XCZDH

New activity in Qwen/Qwen-14B-Chat about 1 month ago

网址拼接的问题

#17 opened 2 months ago by

MaxGavin

New activity in Qwen/Qwen1.5-1.8B about 1 month ago

License clarity, please.

#3 opened 2 months ago by

computerdarren

New activity in Qwen/Qwen-72B-Chat-Int4 about 1 month ago

qwen72B有awq的量化版本吗？

#5 opened 2 months ago by

dongxq

New activity in Qwen/Qwen-VL-Max about 1 month ago

While inputting text prompt and my custom image, when i submit the image i got error response

#8 opened 2 months ago by

aliman80

Error on submit

#2 opened 4 months ago by

alx-ai

New activity in Qwen/Qwen1.5-72B-Chat about 1 month ago

Error when sending message

#13 opened 2 months ago by

lissthings01

New activity in Qwen/Qwen-VL-Max about 1 month ago

The model gives error messages when I upload model.

#7 opened 2 months ago by

AdemSkr

New activity in Qwen/Qwen1.5-14B about 1 month ago

constantly outputting tokens

#4 opened 2 months ago by

nogggg

New activity in Qwen/Qwen-14B-Chat-Int4 about 1 month ago

模型在A10上推理的时候如果设置了temperature会报错

#9 opened 2 months ago by

richard-yao

New activity in Qwen/Qwen1.5-14B-Chat-GPTQ-Int4 about 1 month ago

推理速度有些慢

#3 opened 3 months ago by

yaoye7758521

New activity in Qwen/Qwen1.5-MoE-A2.7B about 1 month ago

Update README.md

#3 opened 2 months ago by

Crystalcareai

New activity in Qwen/Qwen1.5-MoE-A2.7B-Chat about 1 month ago

gguf?

#3 opened 2 months ago by

wukongai

New activity in Qwen/Qwen1.5-MoE-A2.7B about 1 month ago

Why is there only one shared expert in the code?

#4 opened about 2 months ago by

KevinChen1994

New activity in Qwen/Qwen1.5-72B-Chat about 1 month ago

虽然支持32768的上下文但是为啥输入token大于4k就会报oom的错误？？？

#4 opened 3 months ago by

hellohaitao

New activity in Qwen/qwen1.5-MoE-A2.7B-Chat-demo about 1 month ago

How is the inference so fast in this free hardware space?

#1 opened about 2 months ago by

mahiatlinux

New activity in Qwen/Qwen-72B-Chat about 1 month ago

多轮对话的支持

#6 opened about 2 months ago by

cyd0806

New activity in Qwen/Qwen1.5-0.5B about 1 month ago

how to finetune and quantize the qwen1.5 model with gguf

#5 opened about 2 months ago by

huntz47

New activity in Qwen/Qwen1.5-14B-Chat about 1 month ago

不依赖其他推理框架，多轮对话代码如何实现？是否有使用例子？

#10 opened about 2 months ago by

hongfengvv

New activity in Qwen/Qwen1.5-72B-Chat-GPTQ-Int4 about 1 month ago

missing quantize_config.json file

#4 opened about 2 months ago by

aromo17

New activity in Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4 3 months ago

how to get the 473M model from Qwen/Qwen1.5-0.5B-Chat

#1 opened 3 months ago by

chengfeng17

New activity in Qwen/Qwen1.5-7B-Chat 3 months ago

qwen1.5-7b-chat是不是推理起来比qwen1.5-7b快很多

#9 opened 3 months ago by

endNone

New activity in Qwen/Qwen-1_8B-Chat-Int8 3 months ago

ValueError: QWenLMHeadModel does not support Flash Attention 2.0 yet.

#1 opened 3 months ago by

sanjeev-bhandari01

New activity in Qwen/Qwen1.5-7B-Chat-AWQ 3 months ago

had upgraded transformer==4.37.0, the error "KeyError: 'qwen2'" becomes "qwen2 isn't suported yet"

#1 opened 3 months ago by

sdwcn

New activity in Qwen/Qwen1.5-72B-Chat 3 months ago

API key?

#9 opened 3 months ago by

Darius753

New activity in Qwen/Qwen-72B 3 months ago

GQA

#4 opened 5 months ago by

Nexesenex

New activity in Qwen/Qwen-Audio 3 months ago

demo crash？

#2 opened 3 months ago by

YangJiassh

New activity in Qwen/Qwen1.5-14B-Chat-GPTQ-Int4 3 months ago

can't run with fastchat cuda 12.1

#1 opened 3 months ago by

jaywanghz

New activity in Qwen/Qwen1.5-7B-Chat-GPTQ-Int4 3 months ago

The attention mask and the pad token id were not set

#2 opened 4 months ago by

areumtecnologia

CUDA extension not installed

#1 opened 4 months ago by

areumtecnologia

New activity in Qwen/Qwen1.5-72B-Chat 3 months ago

本地启动这个app.py出错

#6 opened 3 months ago by

Moses25

New activity in Qwen/Qwen1.5-7B-Chat-GPTQ-Int8 3 months ago

TypeError: qwen2 is not supported yet.

#1 opened 4 months ago by

n1ghtbar0n

New activity in Qwen/Qwen-7B-Chat 3 months ago

ValueError: unknown ids

5

#38 opened 9 months ago by

allenhaozi

New activity in Qwen/Qwen1.5-0.5B 3 months ago

AttributeError: 'Qwen2TokenizerFast' object has no attribute 'eod_id'

#1 opened 4 months ago by

interstellarninja

New activity in Qwen/Qwen-72B 4 months ago

系统指令在哪设置？

#6 opened 4 months ago by

Moses25

New activity in Qwen/Qwen-14B 4 months ago

finetuning error

#12 opened 4 months ago by

adonlee

New activity in Qwen/Qwen-72B 5 months ago

On how much English token was the model trained onn

#5 opened 5 months ago by

aslawliet

New activity in Qwen/Qwen-7B-Chat 5 months ago

How did you evaluate the Qwen chat models on MMLU (or any other datasets)

#49 opened 5 months ago by

omers66

New activity in Qwen/Qwen-7B 5 months ago

Attempt to add in add_ Special_ Tokens, there is an error, how should I solve it

#19 opened 5 months ago by

wangchengfei

New activity in Qwen/Qwen-14B-Chat 5 months ago

Max sequence length config

#14 opened 5 months ago by

alexhsu

New activity in Qwen/Qwen-72B-Chat 5 months ago

issues about config.json and model.py

#4 opened 5 months ago by

J22

New activity in Qwen/Qwen-14B-Chat 5 months ago

Can you please submit this to leaderboard?

6

#15 opened 5 months ago by

gblazex

New activity in Qwen/Qwen-72B-Chat-Int4 5 months ago

有时候会吐出训练集文本.

10

#2 opened 6 months ago by

kk3dmax

New activity in Qwen/Qwen-1_8B-Chat 5 months ago

Is it possible to pad inputs?

#2 opened 5 months ago by

omers66

New activity in Qwen/Qwen-72B 5 months ago

评测指标

#1 opened 6 months ago by

wlike

Training loss?

#2 opened 6 months ago by

borgr

New activity in Qwen/Qwen-14B 5 months ago

About sft got unstoppable \n when output

#10 opened 6 months ago by

lucasjin

It would be useful if someone spent the time to convert the tokenizer to gpt2 HF format

#9 opened 6 months ago by

KnutJaegersberg

Tokenizer issue

#1 opened 8 months ago by

teknium

Is your Tokenizer following BPE?

#7 opened 7 months ago by

aslawliet

The latest modeling_qwen.py file causing error

#11 opened 6 months ago by

xw

New activity in Qwen/Qwen-7B 5 months ago

Ggml version

#8 opened 10 months ago by

edwardDali

请问贵公司可以开源一个小点的模型吗？

#15 opened 8 months ago by

krisfu

New activity in Qwen/Qwen-14B-Chat-Int4 5 months ago

Request: DOI

#1 opened 8 months ago by

lhfei

Repetitive Output

#2 opened 8 months ago by

BBLL3456

Load bug: slow and mistake?

#3 opened 8 months ago by

XLH

FastChat Load Error

5

#4 opened 8 months ago by

littledot

是否提供AWQ量化版本