社区大使 luispoveda93 基于 OpenBMB 的 MiniCPM5-2B,通过两阶段 LoRA 微调打造出加泰罗尼亚语对话模型 MiniCPM5-2B-catalan-chat-v2。
🌍 “Hola!” from the MiniCPM community!
Meet MiniCPM5-2B-catalan-chat-v2, a Catalan conversational model built by our ambassador luispoveda93 through two-stage LoRA fine-tuning of OpenBMB’s MiniCPM5-2B.
📚 Stage 1 — Single-turn instruction tuning
165,100 examples from Projecte AINA’s InstruCAT dataset, covering Q&A, summarization, paraphrasing, and more.
💬 Stage 2 — Multi-turn conversation
Continued fine-tuning on a ~23.4K chat-focused subset of BSC-LT/ALIA-2606-SFT, focusing on dialogue flow and instruction following across turns.
💻 Ready to explore locally
Merged BF16 weights and LoRA adapters are available, alongside community-contributed GGUF versions for local use with llama.cpp and Ollama.
🛠️ Building for your language? This community project offers a concrete example of adapting MiniCPM with language-specific instructions and dialogue data.
Explore the model 👇
http://huggingface.co/luispoveda93/MiniCPM5-2B-catalan-chat-v2
🚀 Build with MiniCPM5-2B:
GitHub: https://github.com/OpenBMB/MiniCPM
Hugging Face: https://huggingface.co/openbmb/MiniCPM5-2B
#MiniCPM #OpenBMB #Catalan #LoRA #LocalAI
来源:OpenBMB · x.com