GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
ewinregirgojr
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
ewinregirgojr
Model Tree
openbmb/MiniCPM5-1B
Input Modalities
Output Modalities
Supported Functionality
MiniCPM5-1B-Agentic-Tooluse-v3 is fine-tuned specifically for agentic tool/function calling: given a tool schema and a natural-language request, it reliably produces a correctly-named, correctly-structured, correctly-valued function call — the exact capability that powers LangChain/LlamaIndex/AutoGen/CrewAI agents, MCP tool servers, ReAct-style loops, and home-automation assistants.
This release combines QLoRA supervised fine-tuning with a GRPO reinforcement-learning refinement stage, specifically optimized to improve exact function-name selection and exact argument-value correctness — historically the two hardest failure modes for small (~1B) tool-calling models.
| metric | v2 (previous release) | v3 (this model) |
|---|---|---|
| parseable | 0.9933 | 1.0000 |
| valid_name | 0.9700 | 0.9933 |
| expected_name | 0.9067 | 0.9733 |
| args_exact | 0.6133 | 0.7500 |
| arg_key_overlap | 0.8757 | 0.9553 |
args_exact (correct function and every argument value exactly right) is the strictest and most production-relevant metric — this is where the GRPO reinforcement-learning stage delivers the biggest improvement over the prior version.
transformers, vLLM, SGLang, TGI, and any standard Hugging Face causal-LM serving pipelinepython
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16")model = AutoModelForCausalLM.from_pretrained("ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16")# Use tok.apply_chat_template(messages, tools=[...]) with your function/tool schema,# then generate as usual — the model emits a structured function call.
vLLM:
bash
vllm serve ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-Merged-FP16
llama.cpp / Ollama / LM Studio (F16, Q8_0, Q4_K_M): MiniCPM5-1B-Agentic-Tooluse-v3-GGUFDo I need the adapter repo too? No — this repo already contains the fully merged weights. Use the adapter repo only if you want to load it on top of base MiniCPM5-1B yourself or continue fine-tuning.
What's the difference between this and the GGUF repo? This is full-precision FP16 safetensors for GPU-backed serving frameworks (transformers, vLLM, SGLang). The GGUF repo is quantized for CPU-friendly local inference via llama.cpp/Ollama/LM Studio.
How was v3 trained differently from v2? v3 continues from the v2-era recipe with an additional QLoRA SFT pass plus a GRPO reinforcement-learning stage explicitly rewarding exact argument-value correctness, which is what drives the args_exact improvement shown above.
Built on MiniCPM5-1B by OpenBMB.