MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3 — Small Function-Calling LoRA Adapter (GRPO + QLoRA)

MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3 is a LoRA adapter for MiniCPM5-1B that turns a 1-billion-parameter base model into a reliable function-calling / tool-calling agent. Under 100 MB download. Load it with PEFT on top of openbmb/MiniCPM5-1B and run it on a consumer GPU, a laptop, or any edge device.

If you are looking for a small LLM for function calling, a lightweight tool-use LoRA adapter, a local AI agent backbone under 100MB, a cheap fast alternative to GPT-4o / Claude function calling, or a GRPO-trained structured-output model, this adapter is built exactly for that.

74.67% exact-argument accuracy on a held-out 300-example benchmark — trained with QLoRA supervised fine-tuning followed by GRPO reinforcement learning, rewarding exact function-name and argument-value correctness. The adapter itself is under 100 MB.

Why MiniCPM5-1B-Agentic-Tooluse?

• Tiny footprint, real accuracy. 1B parameters, adapter under 100 MB — deployable anywhere a 7B+ model can't go: mobile apps, browser extensions, IoT/embedded agents, offline assistants, cost-sensitive high-throughput API backends.
• Purpose-built for agentic tool use. Trained specifically to parse a tool/function schema plus a natural-language user request and emit a correctly-named, correctly-structured, correctly-valued function call — the core skill every LLM agent framework (LangChain, LlamaIndex, AutoGen, CrewAI, custom ReAct loops, MCP servers) depends on.
• Two-stage training: QLoRA SFT + GRPO reinforcement learning. Most open tool-calling fine-tunes stop at supervised fine-tuning. This adapter adds GRPO (Group Relative Policy Optimization) RL on top, specifically rewarding exact function-name selection and exact argument-value correctness — the two hardest, most failure-prone parts of tool calling for small models.
• Honestly measured, not marketing numbers. Every metric comes from one evaluation harness run end-to-end on a locked, held-out 300-example test split — same parser, same grader, same slice for the base model, the SFT model, and this GRPO-refined v3 adapter.
• Compared to GPT-4o / Claude for function calling: 100% free, fully local, zero per-call cost, fine-tunable, data never leaves your machine.

Why MiniCPM5-1B-Agentic-Tooluse?

• Tiny footprint, real accuracy. 1B parameters total, LoRA adapter itself is under 100MB — deployable anywhere a 7B+ model can't go: mobile apps, browser extensions, IoT/embedded agents, offline assistants, cost-sensitive high-throughput API backends.

• Purpose-built for agentic tool use. Trained specifically to parse a tool/function schema plus a natural-language user request and emit a correctly-named, correctly-structured, correctly-valued function call — the core skill every LLM agent framework (LangChain, LlamaIndex, AutoGen, CrewAI, custom ReAct loops, MCP servers) depends on.

• Two-stage training pipeline: QLoRA SFT + GRPO reinforcement learning. Most open tool-calling fine-tunes stop at supervised fine-tuning. This adapter goes a step further with GRPO (Group Relative Policy Optimization) reinforcement learning on top of the SFT checkpoint, specifically rewarding exact function-name selection and exact argument-value correctness — the two hardest, most failure-prone parts of tool calling for small models.

• Honestly measured, not marketing numbers. Every metric below comes from one single evaluation harness run end-to-end on a locked, held-out 300-example test split — same parser, same grader, same slice, for the base model, the SFT model, and this GRPO-refined v3 model. No cherry-picked runs, no mixed benchmarks.

Results

Evaluated on a held-out 300-example test slice drawn from a seeded shuffle of ToolACE (see Split integrity). The base-model column is the same model with the same prompt and no adapter.

The published weights are SFT + GRPO (see GRPO / RLVR). The SFT column is kept because every negative result below is measured against it.

metric	v2 (previous release)	SFT retrain (pre-GRPO)	v3 = SFT + GRPO (published)
parseable — output is a well-formed call	0.9933	1.0000	1.0000
valid_name — name exists among the offered tools	0.9700	0.9867	0.9867
expected_name — name matches gold	0.9067	0.9567	0.9533
args_exact — every argument value matches gold	0.6133	0.7367	0.7467
arg_key_overlap — F1 over argument keys	0.8757	0.9422	0.9388
mean of 5	0.8718	0.9245	0.9251

GRPO buys +0.0100 on args_exact, the metric that matters here, and gives back 0.0034 (one test example each) on expected_name and arg_key_overlap. That trade is reported rather than hidden: the mean moves only +0.0006, so this is a targeted gain on the hardest metric, not a broad improvement.

Full 8-metric benchmark (held-out test set, n=300)

This table mirrors the evaluation format from v2 and shows Base, v2, and v3 side-by-side across all 8 metrics using a single consistent harness and held-out test slice:

Metric	Base MiniCPM5-1B	v2 (previous release)	v3 (this model)	Delta (v2 → v3)
parseable_rate	0.0133	0.9933	1.0000	+0.0067
valid_name_rate	0.0133	0.9700	0.9867	+0.0167
expected_name_rate	0.0133	0.9267	0.9533	+0.0267
args_exact_rate	0.1500	0.6533	0.7467	+0.0934
arg_key_overlap	0.0033	0.7517	0.9388	+0.1871
no_schema_copy_rate	1.0000	1.0000	0.9967	-0.0033
no_repetition_rate	0.9967	1.0000	0.3400	-0.6600
stopped_cleanly_rate	0.0000	0.1500	0.0000	-0.1500

What the additional metrics mean:

• no_schema_copy_rate — the model did not copy the tool schema's own field description verbatim into an argument value.
• no_repetition_rate — the completion did not contain a duplicated function-call block or degenerate repeated-phrase loop. This model has a known weakness here: it often continues generating filler content after the tool call completes. Use a parser that extracts the first completed <function>...</function> block.
• stopped_cleanly_rate — the model naturally stopped immediately after the completed </function> tag with no trailing tokens. Use a parser that treats the first completed <function>...</function> block as the action boundary — do not rely on natural end-of-generation.

Model details

• Base model: openbmb/MiniCPM5-1B — a compact, efficient, Llama-architecture 1B-parameter language model from OpenBMB, ideal for resource-constrained inference, edge computing, and low-latency serving.

• Adapter type: LoRA (Low-Rank Adaptation) via PEFT, rank r=32, alpha=64, dropout=0.05

• Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj (full attention + MLP coverage)

• Training pipeline: QLoRA supervised fine-tuning on tool-calling / function-calling trajectories → GRPO reinforcement-learning refinement optimizing for exact argument correctness

• Training stack: Unsloth (fast, memory-efficient fine-tuning) + TRL (GRPO trainer) + PEFT

• Format: safetensors, peft library compatible

Quickstart

from transformers import AutoModelForCausalLM, AutoTokenizer

from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("openbmb/MiniCPM5-1B")

tok = AutoTokenizer.from_pretrained("openbmb/MiniCPM5-1B")

model = PeftModel.from_pretrained(base, "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3")

# Use tok.apply_chat_template(..., tools=[...]) with your function/tool schema,

# then generate as usual — the model emits a structured function call.

Prefer not to deal with adapter loading, or want a single-file local build? See the related repos below for a merged full-weight checkpoint and quantized GGUF files for llama.cpp / Ollama / LM Studio.

Ideal use cases

• Local, private, offline AI agents that need to call tools/APIs without sending data to a cloud LLM provider

• Home automation and smart-home assistants (small enough to run on a Raspberry Pi-class device or a home server)

• Mobile and embedded applications where a 7B+ model is impractical

• High-throughput, cost-sensitive backend services orchestrating many tool calls per request

• Any LangChain / LlamaIndex / AutoGen / MCP-based agent that needs a cheap, fast, locally-hostable function-calling backbone

• Research and experimentation on small-model reasoning, LoRA fine-tuning, and RL-based (GRPO) post-training for structured generation

Base model architecture

MiniCPM5-1B uses a standard LlamaForCausalLM architecture:

Property	Value
Parameters (total)	1,080,632,832
Parameters (non-embedding)	679,552,512
Architecture	LlamaForCausalLM
Layers	24
Attention heads (GQA)	16 Q / 2 KV
Context length	131,072 tokens
Training	SFT → RL (GRPO) fine-tune on openbmb/MiniCPM5-1B

Thinking mode

MiniCPM5-1B has a built-in <think>...</think> chat template. The same checkpoint can act as a fast assistant or a deliberate chain-of-thought reasoner — controlled by a single flag:

# Fast mode — recommended for tool calling (thinking OFF)
prompt = tokenizer.apply_chat_template(
    messages, tools=tools, add_generation_prompt=True,
    enable_thinking=False,
    tokenize=False,
)

# Reasoning mode (thinking ON — NOT recommended for tool calling)
prompt = tokenizer.apply_chat_template(
    messages, tools=tools, add_generation_prompt=True,
    enable_thinking=True,
    tokenize=False,
)

Important: always use enable_thinking=False for tool/function calling. With thinking ON the model spends its token budget inside <think>...</think> and may not reach a completed function call. All benchmark numbers in this card use thinking OFF.

Citation

If you use this model, please cite the base model paper:

@article{minicpm4,
  title   = {MiniCPM4: Ultra-Efficient LLMs on End Devices},
  author  = {MiniCPM Team},
  journal = {arXiv preprint arXiv:2506.07900},
  year    = {2025}
}

And the ToolACE dataset used for fine-tuning:

@article{toolace,
  title   = {ToolACE: Winning the Points of LLM Function Calling},
  author  = {Liu, Ying and others},
  journal = {arXiv preprint arXiv:2409.00920},
  year    = {2024}
}

ModelScope

The base model is also available on ModelScope (for users in China and East Asia):

• OpenBMB/MiniCPM5-1B on ModelScope

(The fine-tuned adapter/GGUF builds are currently HuggingFace-only.)

Related repos

v3 model family (this release)

Format	Repository
LoRA adapter (PEFT, smallest download, fine-tune further)	MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3
Merged full-weight FP16 (transformers / vLLM / SGLang serving)	MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16
GGUF quantizations (llama.cpp / Ollama / LM Studio, CPU-friendly)	MiniCPM5-1B-Agentic-Tooluse-v3-GGUF

Previous releases

Format	Repository
v2 LoRA adapter	MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2
v2 Merged FP16	MiniCPM5-1B-Agentic-Tooluse-Merged-FP16
v2 GGUF	MiniCPM5-1B-Agentic-Tooluse-GGUF

FAQ

Is this a full model or an adapter? This repo is a LoRA adapter — small, fast to download, must be loaded on top of the base MiniCPM5-1B model via PEFT. If you want a single ready-to-serve checkpoint, use the Merged-FP16 or GGUF repos linked above instead.

Can I run this on CPU / a laptop / a phone? Yes — the whole point of a 1B-parameter model is that it's small enough for CPU inference, laptops, and (via the GGUF quantized builds) even lower-power edge devices.

How does this compare to using GPT-4o / Claude for function calling? This model trades some absolute accuracy for massive gains in cost, latency, privacy, and deployability — you get a locally-hostable, fine-tunable, fully open-weight alternative for agentic tool-use workloads where sending every request to a large hosted API isn't practical or affordable.

What license is this under? Apache 2.0, matching the base model.

Base model

Built on MiniCPM5-1B by OpenBMB.

Limitations