Update README.md

README.md

@@ -3,21 +3,21 @@ license: cc-by-4.0
 datasets:
 - Salesforce/xlam-function-calling-60k
 - MadeAgents/XLAM-7.5k-Irrelevance
-base_model: Qwen/Qwen2-7B-Instruct
+base_model: Qwen/Qwen1.5-4B-Chat
 ---
-# Hammer-7b Function Calling Model
+# Hammer-4b Function Calling Model
 
 ## Introduction
-Hammer-7b is a cutting-edge Large Language Model (LLM) crafted to boost the critical capability of AI agents: function calling. Differing from existing models focusing on traning data refinement, Hammer-7b optimizes performance primarily through advanced training techniques. 
+Hammer-4b is a cutting-edge Large Language Model (LLM) crafted to boost the critical capability of AI agents: function calling. Differing from existing models focusing on traning data refinement, Hammer-4b optimizes performance primarily through advanced training techniques. 
 
 ## Model Details
-Hammer-7b is a finetuned model built upon [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-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, Hammer-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).
+Hammer-4b is a finetuned model built upon [Qwen1.5-4B-Chat](https://huggingface.co/Qwen/Qwen1.5-4B-Chat). 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, Hammer-4b 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.
 
 ## Evaluation
-First, we evaluate Hammer-7b on the Berkeley Function-Calling Leaderboard (BFCL):
+First, we evaluate Hammer-4b on the Berkeley Function-Calling Leaderboard (BFCL):
 
 <div style="text-align: center;">
     <img src="figures/bfcl.PNG" alt="overview" width="1480" style="margin: auto;">
@@ -32,7 +32,7 @@ In addition, we evaluated our Hammer series (1.5b, 4b, 7b) on other academic ben
 
 
 ## Requiements
-The code of Hammer-7b has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`.
+The code of Hammer-4b has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`.
 
 ## How to Use
 This is a simple example of how to use our model.
@@ -41,7 +41,7 @@ import json
 import torch 
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "MadeAgents/Hammer-7b"
+model_name = "MadeAgents/Hammer-4b"
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(model_name)