Update README.md

README.md

@@ -1,3 +1,15 @@
----
-license: cc-by-4.0
----
+---
+license: cc-by-4.0
+datasets:
+- Salesforce/xlam-function-calling-60k
+base_model:
+- Qwen/Qwen2.5-Coder-1.5B-Instruct
+---
+
+# Hammer2.0-1.5b Function Calling Model
+
+## Introduction
+The Hammer2.0 series models have been released, including versions such as [0.5b](https://huggingface.co/MadeAgents/Hammer2.0-0.5b), [1.5b](https://huggingface.co/MadeAgents/Hammer2.0-1.5b), [3b](https://huggingface.co/MadeAgents/Hammer2.0-3b), and [7b](https://huggingface.co/MadeAgents/Hammer2.0-7b). Compared to the Hammer 1.0 series, the Hammer 2.0 series has stronger performance in function calling.
+Take Hammer2.0-1.5b as an example, it is a fine-tuned model based on [Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct). By training with the APIGen Function Calling Datasets containing 60,000 samples and combining innovative training techniques such as function masking, function shuffling, and prompt optimization, Hammer2.0-1.5b has achieved excellent performance in numerous benchmark tests.
+Whether in the Berkeley Function - Calling Leaderboard or other academic benchmark tests, the Hammer2.0 series models have demonstrated stronger generalization ability and can better meet the needs of users in function calling.
+In short, the Hammer2.0 series models provide users with a more powerful and efficient language model solution.