Update README.md

README.md

@@ -4,4 +4,26 @@ language:
 - en
 base_model:
 - meta-llama/Llama-3.1-70B-Instruct
----
+---
+
+Here's an improved version of your Hugging Face model card in Markdown format, with clearer structure, formatting, and more professional phrasing:
+
+---
+
+# Llama-3.1-70B-Instruct + ToolQA (Finetuned)
+
+This model is based on **Llama-3.1-70B-Instruct**, fine-tuned on the [ToolQA dataset](https://github.com/night-chen/ToolQA) for multi-step tool-use reasoning tasks.
+
+## Training Details
+
+* **Dataset**: [ToolQA](https://github.com/night-chen/ToolQA) – a benchmark designed for evaluating agents' tool-use capabilities in complex environments.
+* **Training Framework**: [Memento-No-More](https://arxiv.org/abs/2502.01562) – a novel framework for teaching models to internalize hints and perform multi-skill reasoning.
+* **Fine-tuning Rounds**: 3
+* **Model Base**: [Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)
+
+## Reference
+
+For detailed information on the training methodology, architecture, and evaluations, please refer to our paper:
+
+> **Alakuijala, M., Gao, Y., Ananov, G., Kaski, S., Marttinen, P., Ilin, A., & Valpola, H.** (2025). *Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization*. arXiv preprint [arXiv:2502.01562](https://arxiv.org/abs/2502.01562).
+