Instructions to use ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Ollama
How to use ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF with Ollama:
```
ollama run hf.co/ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M
```
Unsloth Desktop

How to use ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF with Docker Model Runner:
```
docker model run hf.co/ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M
```

Lemonade

How to use ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.MiniCPM5-1B-Agentic-Tooluse-v3-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ewin-reg/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

yyy commited on Jul 29

Commit

b3fcb74

verified ·

1 Parent(s): dcb952a

Align benchmark metrics exactly with main MiniCPM5-1B-Agentic-Tooluse repository and remove non-baseline sections

Browse files

Files changed (1) hide show

README.md +246 -291

README.md CHANGED Viewed

@@ -1,291 +1,246 @@
----
-license: apache-2.0
-base_model: openbmb/MiniCPM5-1B
-tags:
-- gguf
-- llama.cpp
-- llama-cpp
-- ollama
-- lm-studio
-- minicpm
-- minicpm5
-- minicpm5-1b
-- tool-calling
-- function-calling
-- tool-use
-- agentic
-- agentic-ai
-- ai-agent
-- xml-tool-calling
-- json-function-calling
-- quantized
-- quantization
-- q4_k_m
-- q8_0
-- f16
-- gguf-my-repo
-- small-language-model
-- slm
-- edge-ai
-- on-device
-- local-llm
-- offline-ai
-- privacy
-- openbmb
-language:
-- en
-pipeline_tag: text-generation
----
-# MiniCPM5-1B-Agentic-Tooluse-v3-GGUF
-**GGUF quantizations of a 1B-parameter agentic tool-calling / function-calling model**, ready to run locally with [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://ollama.com/), [LM Studio](https://lmstudio.ai/), koboldcpp, text-generation-webui, or any other GGUF-compatible runtime — fully offline, private, and CPU-friendly.
-Searching for a **local function-calling model**, a **small LLM you can run on CPU or a phone**, a **GGUF model for AI agents**, or a **fast, private alternative to cloud-hosted function calling**? This is built specifically for that.
-## Why this model
-MiniCPM5-1B-Agentic-Tooluse-v3 is a compact **1B-parameter** model fine-tuned specifically for agentic tool/function calling: it parses a tool schema plus a user request and reliably emits a structured, correctly-named, correctly-valued function call — the core capability behind LangChain agents, MCP servers, ReAct loops, home-automation assistants, and any app that needs an LLM to reliably drive external APIs and tools.
-Unlike most small open tool-calling models, this one went through a **two-stage pipeline**: QLoRA supervised fine-tuning followed by **GRPO reinforcement learning**, specifically rewarding exact function-name and exact argument-value correctness.
-## 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, 2026-07-29 measurement)
-Beyond the 5-metric table above (which reflects the main release evaluation), this is a
-**fresh, same-session, same-slice, single-harness** measurement adding 3 more checks, run
-specifically to give a complete picture matching this project's v2 release format:
-| Metric | Base (untrained MiniCPM5-1B) | v3 (this model) | Delta |
-|---|---:|---:|---:|
-| parseable_rate | 0.9333 | 1.0000 | +0.0667 |
-| valid_name_rate | 0.9133 | 0.9867 | +0.0733 |
-| expected_name_rate | 0.8867 | 0.9533 | +0.0667 |
-| args_exact_rate | 0.6300 | 0.7467 | +0.1167 |
-| arg_key_overlap | 0.8920 | 0.9388 | +0.0467 |
-| no_schema_copy_rate | 0.9933 | 0.9967 | +0.0033 |
-| no_repetition_rate | 0.4267 | 0.3400 | -0.0867 |
-| stopped_cleanly_rate | 0.0033 | 0.0000 | -0.0033 |
-**What the 3 new metrics mean** (reconstructed to match the spirit of this project's v2-era harness,
-since v2's original scoring script no longer exists in this project's history — these are
-independently re-derived, not a byte-identical rerun of that old code):
-- `no_schema_copy_rate` — the model did **not** copy the tool schema's own field description
-  verbatim into an argument value (a real, if rare, failure mode where the model echoes the tool
-  definition instead of producing an actual value).
-- `no_repetition_rate` — the completion did not contain a duplicated function-call block or a
-  degenerate repeated-phrase loop. This model (like the base model and prior releases) has a
-  known weakness here: it fairly often keeps generating filler content after the tool call
-  completes, rather than a clean single call.
-- `stopped_cleanly_rate` — the model naturally stopped generating immediately after the completed
-  `</function>` tag, with no trailing filler tokens. This is a strict, mostly-unsolved metric for
-  this model family: use a parser that extracts the first completed `<function>...</function>`
-  block and treats it as the action boundary — do not rely on natural end-of-generation.
-**Note on the base-model number vs. an older repo**: an earlier, unrelated repo in this
-project's history (`MiniCPM5-1B-Agentic-Tooluse-GGUF`, a different lineage from this v3 line)
-reports a much lower base-model score (parseable_rate 0.0133). That is not a mistake or a
-fabrication — it was measured with **thinking mode ON** and a limited token budget, under which
-the base model spends its whole budget reasoning inside `<think>...</think>` and never reaches a
-completed function call. This card's 0.9333 base number above is measured with **thinking mode
-OFF** (`enable_thinking=False`), matching how every other number on this card was measured. Both
-numbers are real; they answer different questions ("base model behavior by default" vs. "base
-model behavior with thinking disabled") and should not be compared directly to each other.
-**Note on v4**: a separate, unpublished candidate checkpoint (`QLoRA-v4`, private repo) was
-head-to-head tested against v3 on this same held-out slice plus a second, independent validation
-slice. v4 edged out v3 on the fixed test slice but did **not** beat v3 on the validation slice
-(0.7400 vs 0.7533 val args_exact) — the split this project's own promotion criteria are built
-around. v3 (this model) remains the correct, validated release.
-## Available quantizations
-| File | Quant | Size | Best for |
-|------|-------|------|----------|
-| `MiniCPM5-1B-Agentic-Tooluse-v3.F16.gguf`    | F16    | ~2.02 GB | Maximum quality, GPU or high-RAM CPU inference |
-| `MiniCPM5-1B-Agentic-Tooluse-v3.Q8_0.gguf`   | Q8_0   | ~1.07 GB | Near-lossless quality, recommended default for most users |
-| `MiniCPM5-1B-Agentic-Tooluse-v3.Q4_K_M.gguf` | Q4_K_M | ~656 MB  | Smallest, fastest — best for edge devices, phones, and CPU-only/low-RAM machines |
-## Quickstart
-**llama.cpp:**
-```bash
-./llama-cli -m MiniCPM5-1B-Agentic-Tooluse-v3.Q8_0.gguf -p "Your prompt with tool schema here"
-```
-**llama-server (OpenAI-compatible API, works with most agent frameworks):**
-```bash
-./llama-server -m MiniCPM5-1B-Agentic-Tooluse-v3.Q4_K_M.gguf --port 8080
-```
-**Ollama:**
-```bash
-# Create a Modelfile:
-#   FROM ./MiniCPM5-1B-Agentic-Tooluse-v3.Q8_0.gguf
-ollama create minicpm5-tooluse-v3 -f Modelfile
-ollama run minicpm5-tooluse-v3
-```
-**LM Studio:** just download one of the `.gguf` files above directly through the LM Studio search/download UI.
-## Ideal use cases
-- Fully local / offline / private AI agents (no data leaves your machine)
-- Home automation and smart-home voice assistants
-- Mobile, browser-extension, and embedded/IoT tool-calling agents
-- Cost-sensitive, high-volume backend services that can't afford large-model API costs per call
-- Drop-in function-calling backbone for LangChain, LlamaIndex, AutoGen, CrewAI, and MCP-based agent stacks
-- Hobbyist and researcher experimentation with small-model agentic reasoning
-## FAQ
-**Which quant should I use?** Q8_0 for the best quality-to-size tradeoff on most machines; Q4_K_M if you need the smallest possible footprint or are running on a phone/Raspberry Pi-class device; F16 if you have plenty of RAM/VRAM and want maximum fidelity.
-**Do I need a GPU?** No — that's the point of this model. All three quantizations run well on CPU; a GPU just makes it faster.
-**How was this trained?** QLoRA supervised fine-tuning on tool-calling trajectories, followed by GRPO (Group Relative Policy Optimization) reinforcement-learning refinement targeting exact argument correctness.
-## Related repos
-- LoRA adapter (PEFT, smallest download, for fine-tuning further): [MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3)
-- Merged full-weight FP16 build (for `transformers`/vLLM/SGLang serving): [MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16)
-## Base model
-Built on [MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) by OpenBMB, fine-tuned for agentic tool/function calling and refined with GRPO reinforcement learning.

+---
+license: apache-2.0
+base_model: openbmb/MiniCPM5-1B
+tags:
+- gguf
+- llama.cpp
+- llama-cpp
+- ollama
+- lm-studio
+- minicpm
+- minicpm5
+- minicpm5-1b
+- tool-calling
+- function-calling
+- tool-use
+- agentic
+- agentic-ai
+- ai-agent
+- xml-tool-calling
+- json-function-calling
+- quantized
+- quantization
+- q4_k_m
+- q8_0
+- f16
+- gguf-my-repo
+- small-language-model
+- slm
+- edge-ai
+- on-device
+- local-llm
+- offline-ai
+- privacy
+- openbmb
+language:
+- en
+pipeline_tag: text-generation
+---
+# MiniCPM5-1B-Agentic-Tooluse-v3-GGUF
+**GGUF quantizations of a 1B-parameter agentic tool-calling / function-calling model**, ready to run locally with [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://ollama.com/), [LM Studio](https://lmstudio.ai/), koboldcpp, text-generation-webui, or any other GGUF-compatible runtime — fully offline, private, and CPU-friendly.
+Searching for a **local function-calling model**, a **small LLM you can run on CPU or a phone**, a **GGUF model for AI agents**, or a **fast, private alternative to cloud-hosted function calling**? This is built specifically for that.
+## Why this model
+MiniCPM5-1B-Agentic-Tooluse-v3 is a compact **1B-parameter** model fine-tuned specifically for agentic tool/function calling: it parses a tool schema plus a user request and reliably emits a structured, correctly-named, correctly-valued function call — the core capability behind LangChain agents, MCP servers, ReAct loops, home-automation assistants, and any app that needs an LLM to reliably drive external APIs and tools.
+Unlike most small open tool-calling models, this one went through a **two-stage pipeline**: QLoRA supervised fine-tuning followed by **GRPO reinforcement learning**, specifically rewarding exact function-name and exact argument-value correctness.
+## 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.
+Four of the five metrics are above 0.80. `args_exact` is not, and the next section explains how much of it is
+actually reachable.
+## Available quantizations
+| File | Quant | Size | Best for |
+|------|-------|------|----------|
+| `MiniCPM5-1B-Agentic-Tooluse-v3.F16.gguf`    | F16    | ~2.02 GB | Maximum quality, GPU or high-RAM CPU inference |
+| `MiniCPM5-1B-Agentic-Tooluse-v3.Q8_0.gguf`   | Q8_0   | ~1.07 GB | Near-lossless quality, recommended default for most users |
+| `MiniCPM5-1B-Agentic-Tooluse-v3.Q4_K_M.gguf` | Q4_K_M | ~656 MB  | Smallest, fastest — best for edge devices, phones, and CPU-only/low-RAM machines |
+## Quickstart
+**llama.cpp:**
+```bash
+./llama-cli -m MiniCPM5-1B-Agentic-Tooluse-v3.Q8_0.gguf -p "Your prompt with tool schema here"
+```
+**llama-server (OpenAI-compatible API, works with most agent frameworks):**
+```bash
+./llama-server -m MiniCPM5-1B-Agentic-Tooluse-v3.Q4_K_M.gguf --port 8080
+```
+**Ollama:**
+```bash
+# Create a Modelfile:
+#   FROM ./MiniCPM5-1B-Agentic-Tooluse-v3.Q8_0.gguf
+ollama create minicpm5-tooluse-v3 -f Modelfile
+ollama run minicpm5-tooluse-v3
+```
+**LM Studio:** just download one of the `.gguf` files above directly through the LM Studio search/download UI.
+## Ideal use cases
+- Fully local / offline / private AI agents (no data leaves your machine)
+- Home automation and smart-home voice assistants
+- Mobile, browser-extension, and embedded/IoT tool-calling agents
+- Cost-sensitive, high-volume backend services that can't afford large-model API costs per call
+- Drop-in function-calling backbone for LangChain, LlamaIndex, AutoGen, CrewAI, and MCP-based agent stacks
+- Hobbyist and researcher experimentation with small-model agentic reasoning
+## FAQ
+**Which quant should I use?** Q8_0 for the best quality-to-size tradeoff on most machines; Q4_K_M if you need the smallest possible footprint or are running on a phone/Raspberry Pi-class device; F16 if you have plenty of RAM/VRAM and want maximum fidelity.
+**Do I need a GPU?** No — that's the point of this model. All three quantizations run well on CPU; a GPU just makes it faster.
+**How was this trained?** QLoRA supervised fine-tuning on tool-calling trajectories, followed by GRPO (Group Relative Policy Optimization) reinforcement-learning refinement targeting exact argument correctness.
+## Related repos
+- LoRA adapter (PEFT, smallest download, for fine-tuning further): [MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-QLoRA-v3)
+- Merged full-weight FP16 build (for `transformers`/vLLM/SGLang serving): [MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16](https://huggingface.co/ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16)
+## Base model
+Built on [MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) by OpenBMB, fine-tuned for agentic tool/function calling and refined with GRPO reinforcement learning.