Update README.md

README.md

@@ -8,25 +8,27 @@ base_model:
 
 # Hammer2.0-7b 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 [Hammer1.0](https://huggingface.co/MadeAgents/Hammer-7b,https://huggingface.co/MadeAgents/Hammer-1.5b,https://huggingface.co/MadeAgents/Hammer-4b) series, the Hammer2.0 series has stronger performance in function calling.
+We're excited to introduce Hammer 2.0, the latest in our Hammer Large Language Models series designed to enhance AI function calling. Differing from existing models focusing on training data refinement, Hammer optimizes performance primarily through advanced training techniques. In this version, we release a number of models with sizes ranging from 0.5B to 7B: 
+[0.5B](https://huggingface.co/MadeAgents/Hammer2.0-0.5b), 
+[1.5B](https://huggingface.co/MadeAgents/Hammer2.0-1.5b), 
+[4B](https://huggingface.co/MadeAgents/Hammer2.0-3b), and  [7B](https://huggingface.co/MadeAgents/Hammer2.0-0.5b). 
 
 ## Model Details
-Take Hammer2.0-7b as an example, it is a fine-tuned model based on [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct). It's trained using the [APIGen Function Calling Datasets](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) containing 60,000 samples, supplemented by [7,500 irrelevance detection data](https://huggingface.co/datasets/MadeAgents/XLAM-7.5k-Irrelevance) we generated. Employing innovative training techniques like function masking, function shuffling, and prompt optimization, Hammer2.0-7b has achieved exceptional performances across numerous benchmarks including [Berkley Function Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard.html), [API-Bank](https://arxiv.org/abs/2304.08244), [Tool-Alpaca](https://arxiv.org/abs/2306.05301), [Nexus Raven](https://github.com/nexusflowai/NexusRaven-V2) and [Seal-Tools](https://arxiv.org/abs/2405.08355).
-
+Hammer2.0 finetuned based on [Qwen 2.5 series](https://huggingface.co/collections/Qwen/qwen25-66e81a666513e518adb90d9e) and [Qwen 2.5 coder series](https://huggingface.co/collections/Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f). It's trained using the [APIGen Function Calling Datasets](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) containing 60,000 samples, supplemented by [7,500 irrelevance detection data](https://huggingface.co/datasets/MadeAgents/XLAM-7.5k-Irrelevance) we generated. Employing innovative training techniques of function masking, function shuffling, and prompt optimization, Hammer2.0 has achieved exceptional performances across numerous benchmarks including [Berkley Function Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard.html), [API-Bank](https://arxiv.org/abs/2304.08244), [Tool-Alpaca](https://arxiv.org/abs/2306.05301), [Nexus Raven](https://github.com/nexusflowai/NexusRaven-V2) and [Seal-Tools](https://arxiv.org/abs/2405.08355).
 
 ## Tuning Details
-Thanks so much for your attention, a report with all the technical details leading to our models will be published soon.
+We will soon release a report detailing our models' technical aspects. Stay tuned!
 
 ## Evaluation
-First, we evaluate Hammer series on the Berkeley Function-Calling Leaderboard (BFCL):
-
+The evaluation result of Hammer2.0 series on the Berkeley Function-Calling Leaderboard (BFCL) are presented in the following table:
 <div style="text-align: center;">
     <img src="v2_figures/bfcl.PNG" alt="overview" width="1000" style="margin: auto;">
 </div>
 
 
-In addition, we evaluated our Hammer2.0 series (0.5b, 1.5b, 3b, 7b) on other academic benchmarks to further show our model's generalization ability:
+In addition, we evaluated Hammer2.0 on other academic benchmarks to further show our model's generalization ability:
 
 |            Model            | Size | Func-Name+Args Det. (F1 Func-Name \| F1 Args) |       |              |       |             |       |                       |       |             |       | F1 Average |       |
 |:---------------------------:|:----:|:---------------------------------------------:|:-----:|:------------:|:-----:|:-----------:|:-----:|:---------------------:|:-----:|:-----------:|:-----:|:----------:|:-----:|
@@ -47,6 +49,8 @@ In addition, we evaluated our Hammer2.0 series (0.5b, 1.5b, 3b, 7b) on other aca
 | Hammer2.0-3B                |  3B  |                     93.6%                     | 84.3% |     83.7%    | 59.0% |    83.1%    | 58.8% |         95.3%         | 91.2% |    92.5%    | 70.5% |    89.6%   | 72.8% |
 | Hammer2.0-7B                |  7B  |                     91.0%                     | 82.1% |     82.5%    | 65.1% |    85.2%    | 59.6% |         96.8%         | 92.7% |    93.0%    | 80.5% |    89.7%   | 76.0% |
 
+On comparison, Hammer 2.0 outperform models with similar sizes and even surpasses many larger models overall. 
+
 ## Requiements
 The code of Hammer2.0-7b has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`.