openbmb/minicpm/minicpm5-finetune

Claude Code and agent skill by openbmb/minicpm

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Pick the right fine-tuning framework for a MiniCPM5-1B base checkpoint and route to a framework-specific cookbook skill. Use when the user wants to SFT / LoRA / DPO / continue-pretrain MiniCPM5 and has not yet committed to a specific framework, or when they say "fine-tune MiniCPM5", "train MiniCPM5", "MiniCPM5 微调", "LoRA MiniCPM5", "继续训练 MiniCPM5".

Install

npx vskill@latest install openbmb/minicpm/minicpm5-finetune

SKILL.md

The same SKILL.md was published earlier as openbmb/minicpm/minicpm5-finetune.

Fine-tune MiniCPM5-1B — framework router

You're being asked to fine-tune MiniCPM5-1B. Pick exactly one framework skill below and invoke that skill rather than improvising — every framework has at least one MiniCPM5-specific gotcha that the dedicated skill knows about.

1. Required input from the user

VariableExampleNotes
BASE_MODELHF id openbmb/MiniCPM5-1B (post-release) or a local pathsee cluster paths below
DATApath to JSONL in messages format[{"messages": [{"role":"user","content":"..."}, {"role":"assistant","content":"..."}]}]
OUTPUT_DIRwhere to write checkpointsmkdir if missing
Goal"LoRA SFT" / "full SFT" / "DPO" / "QLoRA on consumer GPU" / "continue-pretrain at scale"drives skill choice
Hardware1× GPU / multi-nodedrives skill choice
Default base model

If BASE_MODEL is not pinned, default to the Hugging Face fp16 release:

openbmb/MiniCPM5-1B

Any local directory containing config.json + model.safetensors + tokenizer.json also works.

2. Decision matrix — pick exactly one

User says / wantsBest fit→ Skill to invoke
YAML / WebUI driven SFT, broad community supportLLaMA-Factory`minicpm5-finetune-llamafactory`
ChatML template + ModelScope-native SFT/DPO/KTO/ORPOms-swift`minicpm5-finetune-ms-swift`
Bare-metal Python, assistant-only loss, minimal abstractionsTRL + PEFT`minicpm5-finetune-trl`
Single-GPU LoRA / QLoRA, tight VRAM (24 GB or less)unsloth`minicpm5-finetune-unsloth`
mmengine config-driven SFT, OpenMMLab stackxtuner`minicpm5-finetune-xtuner`
Decision shortcuts
  • First time fine-tuning MiniCPM5: pick `minicpm5-finetune-llamafactory` — most documented, fewest surprises.
  • Need DPO / KTO / ORPO: pick `minicpm5-finetune-ms-swift` (best out-of-the-box) or `minicpm5-finetune-trl` (most control).
  • Single 24 GB consumer GPU: pick `minicpm5-finetune-unsloth` with load_in_4bit=True.
  • Target is llama.cpp / Ollama / LM Studio / MiniCPM Desk Pet (GGUF): train with any skill above, then convert the adapter with `minicpm5-finetune-gguf-lora` (PEFT adapter → GGUF LoRA).

3. Invocation contract

Each sub-skill expects BASE_MODEL, DATA, OUTPUT_DIR and outputs an LoRA adapter (or full checkpoint) at OUTPUT_DIR/. Read the picked sub-skill in full before running — every framework has at least one MiniCPM5-specific gotcha:

FrameworkGotcha (skill handles it for you)
LLaMA-Factorytemplate: minicpm5 (needs LLaMA-Factory from source; NOT template: empty / llama3)
ms-swiftmandatory --model_type llama --template chatml flags
TRLtraining-only chat template patch for assistant_only_loss=True
unslothtransformers==4.57.3 pin if vLLM is in the same env
xtunerprompt_template=PROMPT_TEMPLATE.qwen_chat (ChatML), use openai_map_fn for messages-format data, start_factor ≥ 1e-2

4. Universal sanity check after training

Regardless of framework:

bash
# 1. Verify adapter (or full ckpt) was saved
ls "$OUTPUT_DIR" # adapter_model.safetensors + adapter_config.json (LoRA) OR a full HF directory
# 2. Quick inference check (HF-side, works for both LoRA and full)
python -c "
import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained('$BASE_MODEL', torch_dtype=torch.bfloat16, device_map='auto').eval()
model = PeftModel.from_pretrained(base, '$OUTPUT_DIR').eval() # skip this line for full SFT
tok = AutoTokenizer.from_pretrained('$BASE_MODEL')
inputs = tok.apply_chat_template([{'role':'user','content':'1+1=?'}], add_generation_prompt=True, enable_thinking=False, return_tensors='pt').to(model.device)
out = model.generate(inputs, max_new_tokens=32, do_sample=False)
print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
"

Expected: a coherent answer (e.g. "2"). If it's gibberish or empty, training broke (most likely chat template misalignment — ⮕ check the framework's gotcha row above).

5. Don't reinvent: link to the cookbook

Each sub-skill is paired with a one-page cookbook in `docs/finetune/`. The skill is the machine-readable shortcut; the cookbook is the human-readable reference.

6. Next step — deploying the adapter

The adapter at OUTPUT_DIR/ is a PEFT adapter (adapter_model.safetensors). How you ship it depends on the runtime:

  • vLLM / transformers / SGLang (fp16 HF base): load the PEFT adapter directly — no conversion.
  • llama.cpp / Ollama / LM Studio / MiniCPM Desk Pet (GGUF base): convert it to a GGUF LoRA first with `minicpm5-finetune-gguf-lora`, then --lora adapter.gguf (or upload it in the Desk Pet app).

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
9,518
Repository forks
625
7-day trend score
46

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/openbmb/minicpm/minicpm5-finetune/badge)](https://verified-skill.com/skills/openbmb/minicpm/minicpm5-finetune)

Something wrong with this skill or its page? Tell us.