Update README.md

README.md

@@ -20,6 +20,49 @@ This model uses the 4-bits quantization. So you need to install bitsandbytes to
 ```python
 pip install bitsandbytes
 ```
+For inference (streaming):
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import torch
+from transformers import TextIteratorStreamer
+from threading import Thread
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+model_id = "Arthur-LAGACHERIE/Reflection-Gemma-2-2b"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+prompt = """
+### System
+You are a world-class AI system, capable of complex reasoning and reflection. 
+Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. 
+If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.
+Try an answer and see if it's correct before generate the ouput. 
+But don't forget to think very carefully.
+
+### Question
+The question here.
+"""
+
+chat = [
+    { "role": "user", "content": prompt},
+]
+question = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+question = tokenizer(question, return_tensors="pt").to(device)
+streamer = TextIteratorStreamer(tokenizer, skip_prompt=True)
+generation_kwargs = dict(question, streamer=streamer, max_new_tokens=4000)
+thread = Thread(target=model.generate, kwargs=generation_kwargs)
+
+# generate
+thread.start()
+for new_text in streamer:
+    print(new_text, end="")
+```
+
+# Some info
+If you want to know how I fine tune it, what datasets I used and the training code. [See here]()
+
 
 
 # Model Trained Using AutoTrain