Update README.md

README.md

@@ -37,7 +37,7 @@ language:
     <th>PiQA</th>
   </tr>
   <tr>
-    <td><a href="https://huggingface.co/datatab/Yugo55-GPT-v4-4bit/">Yugo55-GPT-v4-4bit</a></td>
+    <td><a href="https://huggingface.co/datatab/Yugo55-GPT-v4-4bit/">*Yugo55-GPT-v4-4bit</a></td>
     <td>51.41</td>
     <td>36.00</td>
     <td>57.51</td>
@@ -95,4 +95,97 @@ models:
 merge_method: linear
 dtype: float16
 
-```
+```
+
+
+## 💻 Usage
+```terminal
+!pip -q install git+https://github.com/huggingface/transformers # need to install from github
+!pip install -q datasets loralib sentencepiece
+!pip -q install bitsandbytes accelerate
+```
+
+```python
+from IPython.display import HTML, display
+
+def set_css():
+  display(HTML('''
+  <style>
+    pre {
+        white-space: pre-wrap;
+    }
+  </style>
+  '''))
+get_ipython().events.register('pre_run_cell', set_css)
+
+```
+
+```python
+import torch
+import transformers
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model = AutoModelForCausalLM.from_pretrained(
+    "datatab/datatab/Yugo55-GPT-v4-4bit", torch_dtype="auto"
+)
+
+tokenizer = AutoTokenizer.from_pretrained(
+    "datatab/datatab/Yugo55-GPT-v4-4bit", torch_dtype="auto"
+)
+
+
+```
+
+```python
+from typing import Optional
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+
+
+def generate(
+    user_content: str, system_content: Optional[str] = ""
+) -> str:
+    system_content = "Odgovoraj uvek na Srpskom jeziku latinica!!! Ispod je uputstvo koje opisuje zadatak, upareno sa unosom koji pruža dodatni kontekst. Napišite odgovor koji na odgovarajući način kompletira zahtev."
+
+    messages = [
+        {
+            "role": "system",
+            "content": system_content,
+        },
+        {"role": "user", "content": user_content},
+    ]
+
+    tokenized_chat = tokenizer.apply_chat_template(
+        messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
+    ).to("cuda")
+
+    text_streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    output = model.generate(
+        tokenized_chat,
+        streamer=text_streamer,
+        max_new_tokens=2048,
+        temperature=0.1,
+        repetition_penalty=1.11,
+        top_p=0.92,
+        top_k=1000,
+        pad_token_id=tokenizer.pad_token_id,
+        eos_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+    )
+
+    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+
+
+```
+
+```python
+generate("Nabroj mi sve planete suncevog sistemai reci mi koja je najveca planeta")
+```
+
+```python
+generate("Koja je razlika između lame, vikune i alpake?")
+```
+
+```python
+generate("Napišite kratku e-poruku Semu Altmanu dajući razloge za GPT-4 otvorenog koda")
+```
+