Rename model
Browse files
    	
        README.md
    CHANGED
    
    | @@ -12,11 +12,11 @@ tags: | |
| 12 | 
             
            ---
         | 
| 13 |  | 
| 14 |  | 
| 15 | 
            -
            # ToolACE-2-8B
         | 
| 16 |  | 
| 17 | 
            -
            ToolACE-2-8B is a  | 
| 18 | 
             
            Compared with [ToolACE-8B](https://huggingface.co/Team-ACE/ToolACE-8B), ToolACE-2-8B enhances the tool-usage ability by self-refinment tuning and task decomposition. 
         | 
| 19 | 
            -
            ToolACE-2-8B achieves a state-of-the-art performance on the [Berkeley Function-Calling Leaderboard(BFCL)](https://gorilla.cs.berkeley.edu/leaderboard.html#leaderboard), rivaling the latest GPT-4 models. 
         | 
| 20 |  | 
| 21 |  | 
| 22 | 
             
            ToolACE is an automatic agentic pipeline designed to generate **A**ccurate, **C**omplex, and div**E**rse tool-learning data. 
         | 
| @@ -42,7 +42,7 @@ Here we provide a code snippet with `apply_chat_template` to show you how to loa | |
| 42 | 
             
            ```python
         | 
| 43 | 
             
            from transformers import AutoModelForCausalLM, AutoTokenizer
         | 
| 44 |  | 
| 45 | 
            -
            model_name = "Team-ACE/ToolACE-2-8B"
         | 
| 46 |  | 
| 47 | 
             
            tokenizer = AutoTokenizer.from_pretrained(model_name)
         | 
| 48 | 
             
            model = AutoModelForCausalLM.from_pretrained(
         | 
|  | |
| 12 | 
             
            ---
         | 
| 13 |  | 
| 14 |  | 
| 15 | 
            +
            # ToolACE-2-Llama-3.1-8B
         | 
| 16 |  | 
| 17 | 
            +
            ToolACE-2-Llama-3.1-8B is a fine-tuned model of LLaMA-3.1-8B-Instruct with our dataset [ToolACE](https://huggingface.co/datasets/Team-ACE/ToolACE) tailored for tool usage. 
         | 
| 18 | 
             
            Compared with [ToolACE-8B](https://huggingface.co/Team-ACE/ToolACE-8B), ToolACE-2-8B enhances the tool-usage ability by self-refinment tuning and task decomposition. 
         | 
| 19 | 
            +
            ToolACE-2-Llama-3.1-8B achieves a state-of-the-art performance on the [Berkeley Function-Calling Leaderboard(BFCL)](https://gorilla.cs.berkeley.edu/leaderboard.html#leaderboard), rivaling the latest GPT-4 models. 
         | 
| 20 |  | 
| 21 |  | 
| 22 | 
             
            ToolACE is an automatic agentic pipeline designed to generate **A**ccurate, **C**omplex, and div**E**rse tool-learning data. 
         | 
|  | |
| 42 | 
             
            ```python
         | 
| 43 | 
             
            from transformers import AutoModelForCausalLM, AutoTokenizer
         | 
| 44 |  | 
| 45 | 
            +
            model_name = "Team-ACE/ToolACE-2-Llama-3.1-8B"
         | 
| 46 |  | 
| 47 | 
             
            tokenizer = AutoTokenizer.from_pretrained(model_name)
         | 
| 48 | 
             
            model = AutoModelForCausalLM.from_pretrained(
         | 

