MiniCPM5-2B 加泰罗尼亚语对话模型发布
🌍 “Hola!” from the MiniCPM community!
社区大使 luispoveda93 基于 OpenBMB 的 MiniCPM5-2B，通过两阶段 LoRA 微调推出加泰罗尼亚语对话模型 MiniCPM5-2B-catalan-chat-v2。第一阶段用 Projecte AINA 的 InstruCAT 数据集 165,100 条样本做单轮指令微调，第二阶段在 BSC-LT/ALIA-2606-SFT 约 23.4K 条对话子集上继续微调多轮对话能力。模型已提供合并后的 BF16 权重、LoRA 适配器及社区贡献的 GGUF 版本，可在 llama.cpp 和 Ollama 本地运行。
正文
🌍 “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 👇 https://t.co/N9X7pXmM3K
🚀 Build with MiniCPM5-2B: GitHub: https://t.co/zaffsLsx5m Hugging Face: https://t.co/TNUu629lXn
#MiniCPM #OpenBMB #Catalan #LoRA #LocalAI