| --- |
| library_name: transformers |
| tags: |
| - tool |
| - function-calling |
| - agent |
| - merge |
| base_model: |
| - Qwen/Qwen3-4B-Instruct-2507 |
| - beyoru/Qwen3-4B-I-1209 |
| - Qwen/Qwen3-4B-Thinking-2507 |
| datasets: |
| - Salesforce/xlam-function-calling-60k |
| - beyoru/xlam-instruct-grpo |
| --- |
| |
|
|
| # 🧠 **Model Card — EvolLLM-Linh** |
|
|
| ### **Model Overview** |
|
|
| **Name:** EvolLLM-Linh |
| **Version:** v1.0 |
| **Release Date:** October 23, 2025 |
| **Base Model:** [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) |
| **Library:** 🤗 *Transformers* |
|
|
|
|
| **Purpose:** |
| EvolLLM-Linh is a fine-tuned large language model designed for **function calling**. |
| It aims to enhance **robustness, accuracy, and dialogue coherence** of LLMs operating in **API-driven or tool-using environments**. |
|
|
| **Key Capabilities:** |
| - Precise and context-aware API invocation |
| - Robust multi-turn dialogue consistency |
| - Adaptive understanding of user preferences and intent shifts |
|
|
|
|
| ### **Evaluation Comparison** |
|
|
| | **Category** | **EvolLLM-Linh** | **GPT-OSS-20B** | **Llama** | **Qwen-2507** | **MinCoder-4B-Expert** | |
| | ------------------------------- | :---------------: | :---------------: | :-------: | :-----------: | :---------------: | |
| | SINGLE TURN – SINGLE FUNCTION | 0.800 | 0.800 | 0.63 | 0.69 | 0.81 | |
| | SINGLE TURN – PARALLEL FUNCTION | 0.660 | 0.620 | 0.16 | 0.51 | 0.66 | |
| | MULTI TURN – USER ADJUST | 0.500 | 0.500 | 0.40 | 0.48 | 0.50 | |
| | MULTI TURN – USER SWITCH | 0.620 | 0.620 | 0.40 | 0.56 | 0.64 | |
| | SIMILAR API CALLS | 0.760 | 0.740 | 0.64 | 0.68 | 0.76 | |
| | USER PREFERENCE HANDLING | 0.600 | 0.640 | 0.62 | 0.64 | 0.60 | |
| | ATOMIC TASK – BOOLEAN | 0.880 | 0.960 | 0.70 | 0.68 | 0.88 | |
| | ATOMIC TASK – ENUM | 0.940 | 0.940 | 0.94 | 0.86 | 0.96 | |
| | ATOMIC TASK – NUMBER | 0.940 | 0.960 | 0.90 | 0.82 | 0.94 | |
| | ATOMIC TASK – LIST | 0.920 | 0.900 | 0.84 | 0.78 | 0.94 | |
| | ATOMIC TASK – OBJECT (DEEP) | 0.580 | 0.520 | 0.32 | 0.36 | 0.62 | |
| | ATOMIC TASK – OBJECT (SHORT) | 0.800 | 0.960 | 0.70 | 0.56 | 0.82 | |
| | **Overall Accuracy** | **0.750 (75.0%)** | **0.760 (76.0%)** | **0.61** | **0.64** | **0.761** | |
|
|
|
|
| --- |
|
|
| > **Note:** |
| > **We evaluate all models with the same configuration.** |
| > If you find any incorrect or inconsistent result, please report it for verification. |
| > This ensures transparency and reproducibility across benchmarks. |
|
|
| ### **Leaderboard Reference** |
| all model are benchmarked using **[ACEBench](https://chenchen0103.github.io/ACEBench/)** — assessing **function calling**, **compositional reasoning**, and **multi-turn interaction**. |
| Results are **internal benchmarks** aligned with ACEBench task categories. |
|
|
| --- |
|
|
| ### **Method** |
| - GRPO (Rule-based reward + self-confidence reward) |
| - Evol Merging |
|
|
| --- |
|
|
| ## **Support me at** |
| <p align="center"> |
| <a href="https://www.buymeacoffee.com/ductransa0g" target="_blank"> |
| <img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" width="150px"> |
| </a> |
| </p> |
| |
| ### **License** |
|
|
| **MIT License** — free for research and non-commercial use with attribution. |
| © 2025 beyoru. |
| --- |
