Qwen/QwQ-32B-Preview · Discussions

#59 opened 3 months ago by

skylerr

Remove CoT prompt from chat template

#58 opened 3 months ago by

SumanthRH

Why is this not in inference api?

#56 opened 3 months ago by

Reality123b

请问你们qwq的prompt是什么？推理有什么特殊设置吗？我这边复现live-codebench只有35～38分。（live-code-bench-0801-1101）

#53 opened 4 months ago by

xxzcc

Does QwQ support function calling?

#52 opened 4 months ago by

nanma

Tried the "strawberry" demo case but got wrong answer😂

#51 opened 4 months ago by

HuggingLianWang

🖐️🖐️ Can we please get a 7B reasoning model? 😎🤗🤗😍

3

#50 opened 4 months ago by

so-anyway

Request: DOI

#49 opened 4 months ago by

daniqt2

Can't reproduce the evaluation result of GPQA dataset

5

#47 opened 4 months ago by

Rinn000

Adding Evaluation Results

#44 opened 5 months ago by

QueCumber

Evaluation Details of QwQ-32B-Preview on LiveCodeBench Benchmark

13

#43 opened 5 months ago by

survivi

Independent Evaluation of QwQ-32B-Preview on MMLU-Pro Benchmark

7

#42 opened 5 months ago by

yaronr

Can't copy the full reasoning

#41 opened 5 months ago by

Hamora

Create bsnwritingservices

#40 opened 5 months ago by

carlo34

https://huggingface.co/Qwen/QwQ-32B-Preview/resolve/main/.gitattributes

#39 opened 5 months ago by

tongtong22

Floating point exception

#38 opened 5 months ago by

zhongqy

My prompt induced infinite loops with QwQ

#35 opened 5 months ago by

hanaoverride

docs: update README.md

#34 opened 5 months ago by

eltociear

Which one is more risky, type 1 or type 2?

#33 opened 5 months ago by

Hanialy

Silly tavern template?

#32 opened 5 months ago by

BigBeavis

Update README.md

#31 opened 5 months ago by

cumanpc

Adding Evaluation Results

#30 opened 5 months ago by

leaderboard-pr-bot

Fine-tuning or system prompt for fiction writing?

OMSRI-SRI-RADHAKRSNA-1728

#28 opened 5 months ago by

advokat

Kkk

#27 opened 5 months ago by

Iksksks

Update README.md

#26 opened 5 months ago by

Will the training code and data be released?

#25 opened 5 months ago by

WbjuSrceu

early exit reasoning inference

#24 opened 5 months ago by

miniTsl

RAG architecture based on the model family qwen2.5

#22 opened 5 months ago by

shevel

This is way too much... USB? Yes. U SB.

3

#21 opened 5 months ago by

imoc

该模型只适合聊天，没有其他能力

#20 opened 5 months ago by

royabcde

trick for less token usage and less halucination

#19 opened 5 months ago by

gopi87

multi GPU inferencing

#18 opened 5 months ago by

cjj2003

Install QwQ 32B Locally - Step by Step Video Tutorial

5

#17 opened 5 months ago by

fahdmirzac

Adds Chinese characters to responses

8

#16 opened 5 months ago by

maxbenk

Problem with specific output format

#15 opened 5 months ago by

sszymczyk

UwU

12

#14 opened 5 months ago by

PotatoOff

About Releasing Some Examples of QWQ's Training Dataset

#13 opened 5 months ago by

tanhuajie2001

Nice name QAQ. I'll later upload a 4.7bpw quantized model if it works.

#12 opened 5 months ago by

imoc

QuietSTAR?

#9 opened 5 months ago by

albatrossbirdie

Inference Speed Benchmark and GPU memeory usage

#8 opened 5 months ago by

Yunxz

Some Badcases

#7 opened 5 months ago by

yirgacheffe

ways to contain the thought process from users for a cleaner interface

#5 opened 5 months ago by

Steelskull

A huge thanks!

#2 opened 5 months ago by

owao

ggggggggg

9