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.
41.3M Pulls 133 Tags Updated 2 years ago
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
21.9M Pulls 199 Tags Updated 1 year ago
Flagship vision-language model of Qwen and also a significant leap from the previous Qwen2-VL.
5.2M Pulls 17 Tags Updated 1 year ago
A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.
262.6K Pulls 5 Tags Updated 1 year ago
Initially built this 7b model to fit in my RTX 4060 with 8GB
20 Pulls 1 Tag Updated 3 days ago
Fast, private code autocomplete: Qwen2.5-Coder-1.5B fine-tuned for fill-in-the-middle with project context. Python, JS, TS.
7 Pulls 1 Tag Updated 3 days ago
https://huggingface.co/unsloth/Qwen2.5-Coder-7B-Instruct-128K-GGUF
103 Pulls 1 Tag Updated 1 week ago
Qwen2.5-1.5B-Instruct (Q4_K_M), tuned for fast local inference — 5.4x faster than the original with verified quality (perplexity +3%, task scores unchanged).
65 Pulls 1 Tag Updated 1 week ago
A highly optimized, fine-tuned Qwen2.5-Coder-1.5B model specifically trained to accurately translate natural language into raw SQL queries.
47 Pulls 3 Tags 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
4,810 Pulls 2 Tags Updated 3 months 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
3,831 Pulls 2 Tags Updated 3 months ago
Qwen2.5-Coder-7B fine-tuned for uncensored code generation. Made by RACER IS OP.
3,068 Pulls 4 Tags Updated 2 months ago
Qwen2.5-7B fine-tuned for uncensored creative writing and roleplay. Made by RACER IS OP.
2,005 Pulls 4 Tags Updated 2 months ago
Uncensored, abliterated build of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct), Alibaba's compact instruct model
2,313 Pulls 2 Tags Updated 3 months ago
Qwen2.5-14B fine-tuned for uncensored creative writing and roleplay. Made by RACER IS OP.
1,542 Pulls 4 Tags Updated 2 months ago
A custom model of Qwen2.5-coder:7B-Instruct with the Qwen2.5-coder:3B-instruct used as a speculative fill model to speed up inference. Primarily made for TabbyML Usage.
2,126 Pulls 1 Tag Updated 4 months ago
Zyx AI is an uncensored friend from the model of Qwen2.5:3b for a better performance in old computers and for a fast and accurate response. Enjoy :D
756 Pulls 2 Tags Updated 5 months ago
466 Pulls 1 Tag Updated 3 months ago
155 Pulls 2 Tags Updated 1 month 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.
200 Pulls 1 Tag Updated 2 months ago