English:
I’m a student and AI enthusiast passionate about making open-source language models more accessible to the Traditional Chinese-speaking community. My focus lies in building lightweight, reasoning-capable models through techniques like Chain-of-Thought and LoRA. I believe language models should serve diverse linguistic cultures, and I’m committed to contributing tools and resources that bridge this gap.
繁體中文:
我是一位人工智慧愛好者,目前專注於打造適合繁體中文語境的開源語言模型。透過 Chain-of-Thought(長鏈思考)與 LoRA 等技術,我致力於開發具備推理能力的小型模型,讓繁體中文用戶也能享有高品質的語言模型體驗。我相信,語言模型應該服務多元的文化語境,而我希望能為此貢獻一份力量。
简体中文:
我是一名人工智能爱好者,专注于构建适用于繁体中文场景的开源语言模型。通过 Chain-of-Thought(链式思维)和 LoRA 等技术,我致力于开发兼具推理能力与轻量级的模型,让繁体中文用户也能享受到优质的语言模型服务。我相信语言模型应服务于多样的文化语境,而我愿意为这个目标持续努力。
Yes, DeepSeek R1's release is impressive. But the real story is what happened in just 7 days after:
- Original release: 8 models, 540K downloads. Just the beginning...
- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5M—nearly 5X the originals.
The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.
When you empower builders, innovation explodes. For everyone. 🚀
The most popular community model? @bartowski's DeepSeek-R1-Distill-Qwen-32B-GGUF version — 1M downloads alone.
5 replies
·
reacted to bartowski's
post with 👍about 2 months ago
While a fix is being implemented (https://github.com/ggml-org/llama.cpp/pull/12957) I want to leave the models up for visibility and continued discussion, but want to prevent accidental downloads of known broken models (even though there are settings that could fix it at runtime for now)
With this goal, I've enabled access requests. I don't really want your data, so I'm sorry that I don't think there's a way around that? But that's what I'm gonna do for now, and I'll remove the gate when a fix is up and verified and I have a chance to re-convert and quantize!