A compact Havenlon-focused Qwen3.5 2B model for execution control, intent-to-action reasoning, policy boundaries, and AI Agent execution risk.
43 Pulls 1 Tag Updated 1 week ago
26.3.7. Update: This model introduces higher-quality reasoning trajectories across domains such as science, instruction-following, and mathematics.
1,057 Pulls 1 Tag Updated 5 months ago
Qwen3.5 2B in Q8_0 quantization. Strong balance of capability and efficiency with 262K context, vision, tool use, and thinking. Ideal for local deployment on consumer hardware.
194 Pulls 1 Tag Updated 1 month ago
WSAI-Heart-Pro 是 WSAI-Heart 系列的 Pro 级正式版本，基于 Qwen3.5-2B-Base 全精度 LoRA 微调。约 2B 参数，端侧部署友好。
59 Pulls 1 Tag Updated 3 months ago
WSAI-Heart-Pro-Exp 是 WSAI-Heart-Pro 的实验版本，基于 Qwen3.5-2B-Base 进行全精度 LoRA 微调。相比0.8B，这次升级到了 2B 参数，共情表达与对话质量均有明显提升，且仍然可以端侧部署。
31 Pulls 1 Tag Updated 3 months ago
German-OCR-Turbo ist ein fine-tuned Vision-Language-Modell basierend auf Qwen3-VL-2B, optimiert für die präzise Texterkennung aus deutschen Rechnungen, Formularen und Geschäftsdokumenten. Das Modell extrahiert strukturierte Daten im Markdown-Format.
1,838 Pulls 1 Tag Updated 8 months ago
测试用
27 Pulls 1 Tag Updated 4 months ago
475 Pulls 2 Tags Updated 6 months ago
Qwen3.5 2B LoRA trained to act like Rocky from Project Hail Mary by Andy Weir.
16 Pulls 1 Tag Updated 3 months ago
Qwen-SEA-LION-v4-32B-IT is a multilingual model which has been pretrained and instruct-tuned for the Southeast Asia region. Developed by AI Singapore and funded by National Research Foundation, Singapore.
341 Pulls 3 Tags Updated 10 months ago
Recommended for transcribing and summarizing text from screenshots.
143 Pulls 1 Tag Updated 8 months ago
OpenReasoning-Nemotron-32B is a large language model (LLM) which is a derivative of Qwen2.5-32B. It is a reasoning model that is post-trained for reasoning about math, code and science solution generation
87 Pulls 1 Tag Updated 10 months ago
DeepSeek-R1-Distill models are fine-tuned based on open-source models, using samples generated by DeepSeek-R1. We slightly change their configs and tokenizers. Please use our setting to run these models.
149.1K Pulls 2 Tags Updated 1 year ago
Adapted for Cline tool / Roo Code use in VS Code fused model , hybrid of DeepSeekR1 and Qwen2.5 coder, from FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview.
4,934 Pulls 2 Tags Updated 1 year ago
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models available in [F16, q8_0, q6_K, q4_K_S]
4,160 Pulls 4 Tags Updated 1 year ago
This is an uncensored version of Tongyi-Zhiwen/QwenLong-L1-32B created with abliteration
3,039 Pulls 5 Tags Updated 1 year ago
3,262 Pulls 1 Tag Updated 1 year ago
DeepSeek-R1-Distill-Qwen-Coder-32B-Fusion-9010 is a mixed model that combines the strengths of two powerful DeepSeek-R1-Distill-Qwen-based models: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated and huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.
2,567 Pulls 6 Tags Updated 1 year ago
Qwen2.5 32B uncensored from Karsh-CAI/Qwen2.5-32B-AGI-Q4_K_M-GGUF
2,245 Pulls 2 Tags Updated 1 year ago
void-1 is a family featuring a 32B model built on Qwen/QwQ-32B for advanced reasoning and efficient text generation, alongside a 7B, 27B model built on Qwen2.5 and Gemma 3 optimized for efficient text generation.
1,718 Pulls 3 Tags Updated 1 year ago