Update README.md

README.md

@@ -13,34 +13,16 @@ widget:
 license: other
 ---
 
-# Model Trained Using AutoTrain
-
-This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
 
 # Usage
 
+This model uses the 4-bits quantization. So you need to install bitsandbytes to use it.
 ```python
+pip install bitsandbytes
+```
 
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model_path = "PATH_TO_THIS_REPO"
 
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-model = AutoModelForCausalLM.from_pretrained(
-    model_path,
-    device_map="auto",
-    torch_dtype='auto'
-).eval()
-
-# Prompt content: "hi"
-messages = [
-    {"role": "user", "content": "hi"}
-]
+# Model Trained Using AutoTrain
 
-input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
-output_ids = model.generate(input_ids.to('cuda'))
-response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
 
-# Model response: "Hello! How can I assist you today?"
-print(response)
-```