AITOPAI热报
Models

社区基于 MiniCPM5-2B 微调出加泰罗尼亚语对话模型

OpenBMB@OpenBMB
Post
View the post
Why we picked it

有加泰语需求或想做小语种微调的可以看看，两阶段 LoRA 流程和数据集都公开，GGUF 版本本地就能跑。

OpenBMB 社区成员 luispoveda93 基于 MiniCPM5-2B 做了两阶段 LoRA 微调，发布加泰罗尼亚语对话模型 MiniCPM5-2B-catalan-chat-v2。第一阶段使用 Projecte AINA 的 InstruCAT 数据集的 165,100 条单轮指令样本，覆盖问答、摘要和改写任务。第二阶段用 BSC-LT/ALIA-2606-SFT 中约 2.34 万条对话子集继续微调多轮对话能力。合并后的 BF16 权重和 LoRA 适配器已开放下载，社区还提供了可配合 llama.cpp 和 Ollama 本地运行的 GGUF 版本。

Original · OpenBMB

🌍 “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

#MiniCPM#OpenBMB#LoRA#开源模型#微调

Keep reading

Recent stories with the same tag or section
ProductsBuildersSelected22:05
MiniCPM-V 4.7 runs 35B MoE on phones via LES

The notable point is that a 35B-class MoE can now run at usable speeds on consumer phones without altering the model itself, since the router still decides which experts execute. Mobile and edge developers can test the setup via the released GitHub code and LES links. The benchmark figure on an iPhone 18 Pro Max gives a concrete comparison point against on-demand expert loading baselines.

#MiniCPM#OpenBMB#LES#on-device AI
OpenBMB@OpenBMBSource
ModelsBuildersSelected21:05
MiniCPM5-2B-Jev turns MiniCPM5-2B into a decision model

Instead of prompting a larger model to output text, the model emits calibrated probabilities over fixed options, which suits ticket routing, eligibility checks and criteria scoring where answers must be machine-readable. Developers can pull the Apache 2.0 weights, adapters and scripts, or wire the /v1/systemone API into existing pipelines. At 2B parameters it targets the same slot where teams might otherwise deploy much larger generative models for classification.

#MiniCPM#OpenBMB#open-source models#fine-tuning
Event
OpenBMB@OpenBMB2 sourcesSource
ProductsBuildersSelected10:53
MiniCPM Spark Program S1 concludes with 16 winning projects

The results show small models like MiniCPM5-2B and MiniCPM-o 4.5 running usefully on consumer hardware, from a Mac mini M4 to an ESP32-S3, without cloud reliance. Builders working on edge deployments can study the winning setups, open scripts and evaluation data on OpenBMB's GitHub and Hugging Face to replicate or extend them. The programme also signals OpenBMB using community challenges to grow its open-source ecosystem internationally.

#MiniCPM#OpenBMB#edge AI#open-source models
OpenBMB@OpenBMBSource
ModelsBuildersSelected21:07
MiniCPM-V 4.7 runs 35B MoE on phones at 20.51 tokens/s

Smarter scheduling, not a smaller model, is what makes a 35B-parameter MoE fit and run fast on consumer phones — no retraining required, since routing stays untouched. Developers building on-device multimodal apps can grab the code and weights from GitHub and Hugging Face to run large models where cloud calls are impractical. It also shows open-source Chinese labs pulling ahead on mobile inference efficiency, a space Apple and Qualcomm stack owners care about.

#MiniCPM#OpenBMB#on-device AI#MoE
OpenBMB@OpenBMBSource