---

license: apache-2.0

base_model: openbmb/MiniCPM5-1B

library_name: peft

tags:

- minicpm

- minicpm5

- minicpm5-1b

- tool-calling

- function-calling

- tool-use

- agentic

- agentic-ai

- ai-agent

- xml-tool-calling

- json-function-calling

- lora

- qlora

- peft

- grpo

- reinforcement-learning

- rlhf

- unsloth

- trl

- openbmb

- text-generation

- conversational

- small-language-model

- slm

- edge-ai

- on-device

- local-llm

- efficient-llm

language:

- en

pipeline_tag: text-generation

---

# 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](https://huggingface.co/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** |

Column meanings, to avoid the ambiguity the word "baseline" invites:
**v2 (previous release)** = the previously published SFT adapter. An earlier draft of this card
mislabeled this column "base model (untrained)" -- that was wrong; it is NOT the raw base model.
The real untrained `openbmb/MiniCPM5-1B`, measured on this same test slice, scores `parseable`
0.9333, `valid_name` 0.9133, `expected_name` 0.8867, `args_exact` 0.6300, `arg_key_overlap` 0.8920.
**SFT retrain** = a fresh SFT pass from v2, prior to GRPO. **v3** = what this repo currently serves.
Every "did it improve?" decision in this card is judged against **v2**, not against the untrained
base model — beating an untrained model is not evidence of anything.

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](https://huggingface.co/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](https://github.com/unslothai/unsloth) (fast, memory-efficient fine-tuning) + [TRL](https://github.com/huggingface/trl) (GRPO trainer) + [PEFT](https://github.com/huggingface/peft)

- **Format:** safetensors, `peft` library compatible

## Quickstart

```python

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

## Related repos

### v3 model family (this release)

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

### Previous releases

| Format | Repository |
|--------|-----------|
| v2 LoRA adapter | [MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v2) |
| v2 Merged FP16 | [MiniCPM5-1B-Agentic-Tooluse-Merged-FP16](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-Merged-FP16) |
| v2 GGUF | [MiniCPM5-1B-Agentic-Tooluse-GGUF](https://huggingface.co/ewinregirgojr/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](https://huggingface.co/openbmb/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](https://huggingface.co/openbmb/MiniCPM5-1B) by OpenBMB.