Update README.md

README.md

@@ -19,4 +19,59 @@ base_model: unsloth/mistral-7b-v0.3-bnb-4bit
 
 This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+# install dependencies in google colab
+
+```shell
+!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
+!pip install --no-deps xformers "trl<0.9.0" peft accelerate bitsandbytes
+```
+
+# inference
+```python
+
+from unsloth import FastLanguageModel
+from typing import Dict, List, Tuple, Union, Any
+import pandas
+from tqdm import trange, tqdm
+import torch
+
+class FormatPrompt_QA_with_citation():
+    '''format prompt class'''
+    def __init__(self, eos_token:str='</s>') -> None:
+        self.inputs = ['context','question'] # required input fields
+        self.outputs = ['answer', 'citation'] #  for training, and model inference output fields
+        self.eos_token = eos_token
+
+    def __call__(self, instance: Dict[str, Any]) -> str:
+        '''
+        function call operator 
+        Args:
+            instance: dictionary with keys: 'question', 'answer'
+        Returns:
+            prompt: formatted prompt
+        '''
+        return self.formatting_prompt_func(instance)
+    
+    def formatting_prompt_func(self, instance: dict) -> str:
+        '''format prompt for domain specific QA
+        note this is for fine-tuning pre-trained model,
+        if starting with instuct tuned model, use `tokenizer.apply_chat_template(messages)` instead
+        '''
+
+        assert all([ item in instance.keys()  for item in self.inputs ]), logging.info(f"instance must have {self.inputs}!")
+        
+        prompt = f"""<s> [INST] Context: {str(instance["context"])}\
+        Question: {str(instance["question"])} [/INST]
+        Answer: """
+
+        if ('answer' in instance):
+            if ('citation' in instance):
+                answer = {"answer":str(instance['answer']), "citation":str(instance['citation'])}
+            else:
+                answer = {"answer":str(instance['answer']), "citation":""}
+            prompt += json.dumps(answer, ensure_ascii=False) + self.eos_token # json format
+        else:
+            pass
+        return prompt
+```