Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.
34.8M Pulls 133 Tags Updated 1 year ago
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
18.6M Pulls 199 Tags Updated 1 year ago
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
3.2M Pulls 17 Tags Updated 1 year ago
Qwen2 is a new series of large language models from Alibaba group
6M Pulls 97 Tags Updated 1 year ago
Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).
1.1M Pulls 52 Tags Updated 1 year ago
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
251.4K Pulls 5 Tags Updated 1 year ago
Enterprise coding & engineering assistant by GOCOSYS Technologies — built on Qwen2.5-Coder-7B. Great for PHP, Laravel, Python, JS/TS, React, Node, Docker & DevOps.
39 Pulls 1 Tag Updated 2 days ago
A decensored 1.5B model with strong instruction-following and suppressed refusal behavior.
12 Pulls 4 Tags Updated 14 hours ago
An intelligent AI companion for developers, makers, and innovators—built to think, create, and solve alongside you. Built on top of qwen2.5:3b
8 Pulls 1 Tag Updated 6 days ago
A decensored general-purpose 0.5B model with suppressed refusal behavior, ideal for edge deployment.
4 Pulls 4 Tags Updated 14 hours ago
A decensored code-oriented 0.5B model with suppressed refusal behavior, ideal for local coding agents.
3 Pulls 4 Tags Updated 15 hours ago
Modelo de asistencia Odin basado en qwen2.5:1.5B liviano y rapido para el asistente homonimo de sistema operativo.
2 Pulls 1 Tag Updated 6 days ago
An ai model based on qwen2.5:3b made with specific instructions to be able to comply with the prompt of the official minecraft verity mod greatly.
4,919 Pulls 1 Tag Updated 1 week ago
Uncensored, abliterated build of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct), Alibaba's capable 14B instruct model
952 Pulls 2 Tags Updated 3 weeks ago
Uncensored, abliterated build of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct), Alibaba's flagship 14B coding model
767 Pulls 2 Tags Updated 3 weeks ago
Uncensored, abliterated build of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct), Alibaba's compact instruct model
525 Pulls 2 Tags Updated 3 weeks ago
231 Pulls 1 Tag Updated 3 weeks ago
Bob: senior PHP & Laravel assistant on Qwen2.5-Coder 7B. Detects Laravel 10–13 from your project, gives version-specific answers. Eloquent, APIs, queues, Sanctum, testing. Run: ollama run bhavingajjar/qwen2.5-7b-laravel-coder
97 Pulls 1 Tag Updated 2 weeks ago
A QLoRA fine-tune of Qwen2.5-Coder-1.5B into a terse, code-first Python assistant — 78% shorter answers, trained on a single 8 GB GPU.
70 Pulls 1 Tag Updated 1 week ago
A lightweight, FIM (Fill-In-the-Middle) optimized variant of Qwen2.5-Coder-0.5B-Instruct using the fp16 GGUF quantization from HuggingFace. At only ~1 GB, it fits comfortably on any 8 GB single GPU with headroom for 8K context.
89 Pulls 1 Tag Updated 4 weeks ago