add use code to README

README.md

@@ -101,4 +101,88 @@ MARS have been tranied for 3 days on 4xA100.
 
 - **Base Model**: Meta Llama 3 8B Instruct
 - **Training Dataset**: In-house & Translated Open Source Turkish Datasets
-- **Training Method**: LoRA Fine Tuning
+- **Training Method**: LoRA Fine Tuning
+
+
+## How to use
+
+You can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the `generate()` function. Let's see examples of both.
+
+### Transformers pipeline
+
+```python
+import transformers
+import torch
+
+model_id = "curiositytech/MARS"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "Sen korsan gibi konuşan bir korsan chatbotsun!"},
+    {"role": "user", "content": "Sen kimsin?"},
+]
+
+terminators = [
+    pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+print(outputs[0]["generated_text"][-1])
+```
+
+### Transformers AutoModelForCausalLM
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "curiositytech/MARS"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "Sen korsan gibi konuşan bir korsan chatbotsun!"},
+    {"role": "user", "content": "Sen kimsin?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+```