undfined/dapo-math-17k-processed-filtered-qwen3-4b-base-32samples-ds ...
Qwen3 4B Unsloth Bnb 4bit By unsloth: Benchmarks, Features and Detailed ...
重磅！阿里开源第三代千问大模型：Qwen3系列，最小仅6亿参数规模，最大2350亿参数规模大模型！可以根据问题难度自动选择是否带思考过程的大 ...
DAPO-Math-17K：一个包含17,000个数学问题及其整数答案的数据集，专为大规模LLM强化学习设计，经过精心转换以确保准确的奖励信号 ...
SVRL/verl-scalable-0827_batch128_ppomini32_general-reasoner-megamath ...
Amoral Qwen3 4B By fakezeta: Benchmarks, Features and Detailed Analysis ...
Qwen3-Max 2025 Complete Release Analysis: In-Depth Review of Alibaba's ...
AzalKhan/Qwen2.5-1.5B-Instruct_BF16_open-r1-DAPO-Math-17k-Processed ...
chat_template.jinja · TeichAI/Qwen3-4B-Thinking-2507-DeepSeek-v3.2 ...
yoonholee/completions_qwen3_4blrablation_filtered_0503_lr1e6_Qwen3-4B ...
rubricreward/reasoning-rubric-dataset-qwen3-4b-filtered-r1-max-8192 ...
ljvmiranda921/details_msde-Qwen_Qwen3-8B-Base-lora-4bit-msde-S1-ar ...
GitHub - QwenLM/Qwen2.5-Math: A series of math-specific large language ...
Qwen 2.5 di Alibaba è il miglior modello open-source in matematica e ...
mlfoundations-cua-dev/qwen-7b-grpo-on-103k-filtered-data-dynamic ...
RyanYr/grpo-dapo-qwen2.5math-1.5B-base-mbs64-n4_actor_sd4_matheval ...
Alibaba's AI model Qwen 2.5 Max emerges victorious over Deepseek ...
cg666/Qwen-2.5-Base-7B-gen8-scale-MATH-lighteval-olympiads_aime-ghpo ...
Alibaba’s Qwen 2.5: Dominating Open-Source AI in Math, Coding, and ...
mothnaZl/Qwen2.5-Math-7B-best_of_n-DeepSeek-R1-Distill-Qwen-32B ...
daixuancheng/zero_qwen-math-7b_base_allDapo_mathVerify_yesSuffix ...
Lancement de Qwen2 : le plus puissant modèle linguistique open source d ...
【RL系列】DAPO: An Open-Source LLM Reinforcement Learning System at Scale ...
Alibaba’s Qwen AI Releases Compact Dense Qwen3-VL 4B/8B (Instruct ...
【candle】（3）：安装rust环境，使用GPU进行加速，成功运行qwen的0.5b，4b，7b模型，搭建rust环境，配置candle ...
Qwen发布4B端侧大模型，AIME25性能领先Claude 4 Opus！_qwen3-4b-instruct-2507和qwen2.5 ...
Qwen3-VL双版本重磅发布：2B轻量与32B高性能模型重塑多模态AI应用格局_陆骊咪Durwin-ModelEngine社区
深夜突袭，阿里Qwen3登顶全球开源王座！暴击DeepSeek-R1，2小时狂揽17k星 | 人人都是产品经理
dengcao/Qwen3-Embedding-4B
NVFP4/Qwen3-Coder-30B-A3B-Instruct-FP4 · Hugging Face
Qwen3 From Scratch | Sebastian Raschka, PhD
qwen3:4b-instruct-2507-fp16
项目首页 - Qwen3-VL-4B-Instruct - GitCode
连夜读完了Qwen3的2000行代码，我画出了Qwen3的结构图_qwen3结构图-CSDN博客
全新开源通义千问Qwen3模型系列特性与能力详解-开发者社区-阿里云
Qwen/Qwen3-4B-Thinking-2507-FP8 · Hugging Face
DAPO-Math-17k
yujunzhou/MATH-TTT-Qwen3-4B-Base-Semantic · Hugging Face
README.md · florentgbelidji/Qwen3-4B-Base-SFT-20260120102752 at main
qwen3:4b-thinking-2507-fp16
hdong0/Qwen3-8B-base-Open-R1-GRPO_dapo_acc_16384_nokl · Hugging Face
Qwen3 4B | Open Laboratory
open-r1/DAPO-Math-17k-Processed · Datasets at Hugging Face
ai-models/Qwen/Qwen3-VL-4B-Instruct-GGUF · Cloud Native Build
Qwen3-4B: Specifications and GPU VRAM Requirements
Qwen3: Think Deeper, Act Faster | Qwen
qwen3、gemma3 GPRO强化训练案例_深度学习-CSDN专栏
Qwen3 4b Zimage Clip Candidates - a scruffynerf Collection
最强开源大模型？Qwen3 系列深度解析 + 本地部署指南！_qwen3本地部署-CSDN博客
Qwen/Qwen3-4B-Base · Hugging Face
Qwen3技术报告 - 知乎
Quantized Models for Cannae-AI/Qwen3-MATH-R1-4B – Hugging Face
Windows 10 本地化部署 Qwen3 4B 大模型完整指南：从环境配置到交互实战-CSDN博客
DAPO-Math-17k-Processed
40亿参数改写企业AI规则：Qwen3-4B-Base引爆轻量化革命-CSDN博客
千问3-4B-Base
DAPO-Math-17k|数学学习数据集|算法训练数据集
qwen3:4b-instruct-2507-q4_K_M
Qwen3-ASR 本地部署 | Jckling's Blog
大模型-qwen3 模型结构解读-66 - jack-chen666 - 博客园
Qwen3-Omni：阿里开源全模态大模型，32项SOTA性能重新定义AI交互_gitblog_00057-ModelScope魔搭社区
unsloth/Qwen3-14B-Base-unsloth-bnb-4bit · Hugging Face
Qwen
Qwen/Qwen3-4B · Use the more common reverse filter in template
Qwen3技术全景解析：混合思维架构，MoE设计与DeepSeek深度对比_qwen3的dense和moe模型区别-CSDN博客
从qwen3-next学习大模型前沿架构_zero-centered rmsnorm-CSDN博客
DAPO-Math-17K|数学问题解答数据集|教育技术数据集
字节开源 DAPO：超越 DeepSeek GRPO - 知乎
Qwen3 14B | Open Laboratory
Qwen3-VL-4B Instruct vs Qwen3-VL-4B Thinking: Complete 2025 Guide
robertou2/task-7-Qwen-Qwen3-4B-Base · Discussions
Qwen-Image/README.md at main · QwenLM/Qwen-Image · GitHub
config.yaml · RyanYr/brm-dapo-qwen2.5math-1.5B-base-lr5e-7-beta0.01 at main
Qwen2-Math - 阿里推出的数学专用开源AI模型 | AI工具集
c01zaut/Qwen2.5-Math-7B-Instruct-RK3588-1.1.4 · Hugging Face
RyanYr/ppo-dapo-qwen2.5math-7B-base-lr-mbs64_critic at main
Qwen2.5-Math - 阿里Qwen团队开源的数学专项模型，超越GPT-4o | AI工具集
BytedTsinghua-SIA/DAPO-Math-17k · Datasets at Hugging Face
qwen2.5-coder:32b-instruct-q5_1
视觉语言模型应用开发——Qwen 2.5 VL模型视频理解与定位能力深度解析及实践指南 - 技术栈
LLM - Qwen-72B LoRA 训练与推理实战_qwen 模型的q-lora推理-CSDN博客
DAPO详解 - 知乎
jnanliu/orz-math-filtered-qwen-72b-rollout · Datasets at Hugging Face
DAPO-Math-17K-cleaned|数学问题解答数据集|自然语言处理数据集
Qwen/Qwen2-7B-Instruct · Math problems
阿里的通义千问也能本地部署了？首发Qwen-VL-Chat模型的本地部署教程（A卡）_木法星人-GitCode 开源社区
Qwen 1.5 4B Chat - API, Providers, Stats | OpenRouter
