issues
search
QwenLM
/
Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Apache License 2.0
13.59k
stars
1.11k
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
💡 [REQUEST] - <使用ollama来调用qwen:14B时,怎么设置输出文本长度呢>
#1243
chaoskklt
closed
4 months ago
1
微调完成后使用llama_factory的vllm和qwen官方的vllm部署方式启动返回的不一样
#1241
lxb0425
closed
4 months ago
2
请问可以使用高通的npu进行部署和推理吗?
#1240
caramel678
closed
4 months ago
1
[BUG] <title>执行eval中的eval_plugin进行评测 有一个agent从huggingface_hub拉包错误
#1239
Plutowithcharon
closed
4 months ago
1
请问哪里可以找到qwen用于vllm的jinja template?
#1236
xudong2019
closed
5 months ago
1
[BUG] Function Calling 示例有错误,最新的 openai sdk 运行时提示 api 已经废弃
#1234
henryyan
closed
5 months ago
2
[BUG] <Qwen-14B-Chat 输入长文本时无输出结果>
#1232
TianWuYuJiangHenShou
closed
4 months ago
5
[BUG] <关于model.generate时发现的源码错误>
#1231
malidong521
closed
5 months ago
2
💡 [REQUEST] - <title> 关于lora 模型合并的几个问题
#1226
wangyao123456a
closed
4 months ago
4
Create stale.yml
#1225
jklj077
closed
5 months ago
0
请问基于qwen-72b-chat,基于怎样的配置可以在一台4090上训练起来?
#1224
taishan1994
closed
5 months ago
4
Qwen/eval中的评测CEval和CMMLU,开大推理的batchsize评测指标会显著降低
#1223
ntz2000
closed
4 months ago
1
[BUG] Qwen/Qwen-72B-Chat-Int8,不能多GPU并行计算
#1222
gquanma
closed
5 months ago
1
[BUG] lora微调后,合并成一个模型。这种方式如何加载且推理
#1220
wangyao123456a
closed
4 months ago
4
tokenizer.decoder 抛出'utf-8' codec can't decode bytes in position 1-2: unexpected end of data异常
#1218
gaokao123
closed
5 months ago
2
[BUG] <title>lora微调loss异常?
#1214
estuday
closed
3 months ago
8
如何添加`LogitsProcessor`控制结果输出?
#1213
ChamfersChen
closed
4 months ago
1
[BUG] <title>batch_infer报错:'tuple' object has no attribute 'dtype'
#1210
PineappleWill
closed
4 months ago
3
[BUG] <title> wrong system prompt check?
#1209
XpastaX
closed
5 months ago
2
pip install csrc/layer_norm 不成功
#1208
niykx
closed
4 months ago
2
Run Qwen /openai_api.py, Error :Input should be a valid string, body.messages[3].function_call,请问Qwen1.5不支持了么?
#1205
goqw
closed
5 months ago
1
how to convert qwen.tiktoken to tokenzier.model
#1204
cloudyuyuyu
closed
5 months ago
1
[BUG] .CalledProcessError: Command '['/usr/bin/gcc', '/tmp/tmpecd6su1w/main.c'
#1199
ff1Zzd
closed
5 months ago
3
[BUG] CUDA Error: invalid device function /tmp/pip-req-build-5rlg4jgm/ln_fwd_kernels.cuh 236
#1198
taoqinghua
closed
5 months ago
4
[BUG] <title> 如何用vllm部署qlora后的模型
#1197
KevinFan0
closed
4 months ago
2
指定了模型地址,还是提示 Incorrect path_or_model_id: '/data/shared/Qwen/Qwen-Chat/'
#1196
nikooooooooooooooooooo
closed
5 months ago
0
更改模型地址
#1194
almost-zhengming
closed
5 months ago
0
[BUG] <title> code_interpreter 生成的图像只能生成到阿里云上么,不能不传到云上,只在本地保存么?
#1193
cheng18175030250
closed
5 months ago
2
💡 [REQUEST] - <title>数据集构造方法请教
#1191
skyantao
closed
4 months ago
1
openai_api.py启动的时候添加了username/password, 然后调用的时候怎么传入username/password呢?
#1190
zengqingfu1442
closed
5 months ago
1
[HELP] I wonder how the MMLU result is evaluated?
#1189
YuMeng2v
closed
4 months ago
3
请教,qlora微调没效果
#1188
huangyunxin
closed
6 months ago
1
May I ask when Lisa fine-tuning is supported?
#1187
zhaoyinjiang9825
closed
6 months ago
1
微调过程中的taskType参数
#1186
12915494174
closed
6 months ago
1
多卡并行微调卡住
#1183
HooRin
closed
4 months ago
4
Calculate language probabilities
#1180
itlittlekou
closed
6 months ago
1
4张卡为什么没有并发推理
#1179
linzm1007
closed
6 months ago
5
[BUG] 对qwen-7b模型微调后,输出句子断句不正常,直接从句子中间停止
#1178
twwch
closed
6 months ago
5
请问计划什么时间支持让vllm-gptq运行Qwen-72B-Chat-INT8大模型?
#1176
linklogis-copilot
closed
6 months ago
2
deepspeed 单机多卡训练报错
#1175
GXKIM
closed
6 months ago
6
7B模型推理时生成非有效的idx,应该怎么处理?
#1174
AACengineer
closed
6 months ago
1
[BUG] <title>cannot import name 'allow_in_graph' from partially initialized module 'torch._dynamo' (most likely due to a circular import) (/demo/miniconda3/envs/qwen/lib/python3.9/site-packages/torch/_dynamo/__init__.py)
#1173
dshwei
closed
6 months ago
1
在使用多卡做Qwen-7B-Chat做微调过程中出现ValueError: Expected a string path to an existing deepspeed config, or a dictionary, or a base64 encoded string. Received: finetune/ds_config_zero3.json
#1171
TuDaCheng
closed
6 months ago
1
qwen-14B-chat-int8/4 vllm模式部署错误:no kernel image is available for execution on the device
#1169
Lzzycola
closed
6 months ago
1
以lora、bfloat16方式微调模型,模型微调后采用lora参数和基座模型进行推理,使用merge_and_unload()类前后推理结果不一致,为什么会出现这种情况呢
#1168
shaojh1
closed
4 months ago
4
損失函數計算(評估)方式
#1167
swilly0906
closed
6 months ago
1
微调加载微调模型显存不够,RuntimeError: CUDA error: invalid device ordinal CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions
#1165
xvgaoxing2023
closed
6 months ago
2
💡 [REQUEST] - <title>
#1164
fangmeichuan
closed
6 months ago
2
想请问模型合并的时候没有看到原模型是怎么加路径的,只看到lora权重路径
#1163
GXKIM
closed
6 months ago
3
文档阅读的千问大模型
#1162
474420502
closed
6 months ago
1
Previous
Next