Update README.md

README.md

@@ -16,14 +16,22 @@ We opensource our **Aquila2** series, now including **Aquila2**, the base langua
 
 The additional details of the Aquila model will be presented in the official technical report. Please stay tuned for updates on official channels.
 
+## Updates 2024.6.6
+
+We have updated the basic language model **Aquila2-7B**, which has the following advantages compared to the previous model:
+
+* Replaced tokenizer with higher compression ratio:
+
+| Tokenizer | Size  | Zh                       | En     | Code  | Math   | Average |
+|-----------|-------|--------------------------|--------|-------|-------|---------|
+| Aquila2-original   | 100k  | **4.70**                 | 4.42   | 3.20  | 3.77  | 4.02    |
+| Qwen1.5   | 151k  | 4.27                     | 4.51   | 3.62  | 3.35  | 3.94    |
+| Llama3    | 128k  | 3.45                     | **4.61**   | 3.77  | **3.88** | 3.93    |
+| Aquila2-new     | 143k  | 4.60                     | **4.61** | **3.78** | **3.88**  | **4.22** |
+
+* The maximum processing length supported by the model has increased from 2048 to 8192
 
-## Base Model Performance
 
-<br>
-<p align="center">
-    <img src="base_metrics.jpeg" width="1024"/>
-<p>
-<br>
 
 ## Quick Start  Aquila2-7B
 
@@ -32,34 +40,43 @@ Aquila2-7B is a base model that can be used for continuation.
 
 ```python
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers import BitsAndBytesConfig
 
-device = torch.device("cuda")
-model_info = "BAAI/Aquila2-7B"
-tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
+device= "cuda:0"
+
+# Model Name
+model_name = 'BAAI/Aquila2-7B'
+
+# load model and tokenizer
 quantization_config=BitsAndBytesConfig(
                         load_in_4bit=True,
                         bnb_4bit_use_double_quant=True,
                         bnb_4bit_quant_type="nf4",
                         bnb_4bit_compute_dtype=torch.bfloat16,
                     )
-model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True, torch_dtype=torch.float16,
-                                                # quantization_config=quantization_config, # Uncomment this line for 4bit quantization
-                                                )
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True,
+                        # quantization_config=quantization_config # Uncomment this one for 4-bit quantization
+                        )
+
+tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
+
 model.eval()
+
 model.to(device)
-text = "杭州亚运会的亮点和期待 2023年9月23日至10月8日，杭州将举办第19届亚洲运动会"
+
+# Example
+text = "The meaning of life is"
 tokens = tokenizer.encode_plus(text)['input_ids']
 tokens = torch.tensor(tokens)[None,].to(device)
-stop_tokens = ["###", "[UNK]", "</s>"]
+
 with torch.no_grad():
-    out = model.generate(tokens, do_sample=True, max_length=512, eos_token_id=100007, bad_words_ids=[[tokenizer.encode(token)[0] for token in stop_tokens]])[0]
-    out = tokenizer.decode(out.cpu().numpy().tolist())
-    print(out)
+        out = llama.generate(tokens, do_sample=False, max_length=128, eos_token_id=tokenizer.eos_token_id)[0]
+        out = tokenizer.decode(out.cpu().numpy().tolist())
+        print(out)
 ```
 
 
 ## License
 
-Aquila2 series open-source model is licensed under [ BAAI Aquila Model Licence Agreement](https://huggingface.co/BAAI/Aquila2-7B/blob/main/BAAI-Aquila-Model-License%20-Agreement.pdf)
+Aquila2 series open-source model is licensed under [ BAAI Aquila Model Licence Agreement](https://huggingface.co/BAAI/Aquila2-7B/blob/main/BAAI-Aquila-Model-License%20-Agreement.pdf)