Update README.md

README.md

@@ -56,7 +56,7 @@ llm.create_chat_completion(
 	messages = [
 		{
 			"role": "user",
-			"content": inference_prompt.format("selam alikum, tu çawa yî?")
+			"content": inference_prompt.format("سڵاو ئەلیکوم، چۆنیت؟")
 		}
 	]
 )
@@ -75,8 +75,19 @@ llm.create_chat_completion(
 #### Transformers
 
 ```python
+from http.client import responses
+
+import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
+infer_prompt = """Li jêr rêwerzek heye ku peywirek rave dike, bi têketinek ku çarçoveyek din peyda dike ve tê hev kirin. Bersivek ku daxwazê ​​bi guncan temam dike binivîsin.
+### Telîmat:
+{}
+### Têketin:
+{}
+### Bersiv:
+"""
+
 model_id = "nazimali/Mistral-Nemo-Kurdish-Instruct"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
@@ -93,6 +104,39 @@ model = AutoModelForCausalLM.from_pretrained(
     quantization_config=bnb_config,
     device_map="auto",
 )
+
+model.eval()
+
+
+def call_llm(user_input, instructions=None):
+    instructions = instructions or "tu arîkarek alîkar î"
+    prompt = infer_prompt.format(instructions, user_input)
+
+    input_ids = tokenizer(
+        prompt,
+        return_tensors="pt",
+        add_special_tokens=False,
+        return_token_type_ids=False,
+    ).to("cuda")
+
+    with torch.inference_mode():
+        generated_ids = model.generate(
+            **input_ids,
+            max_new_tokens=120,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.7,
+            num_return_sequences=1,
+            pad_token_id=tokenizer.pad_token_id,
+            eos_token_id=tokenizer.eos_token_id,
+        )
+
+    decoded_output = tokenizer.batch_decode(generated_ids)[0]
+
+    return decoded_output.replace(prompt, "").replace("</s>", "")
+
+response = call_llm("سڵاو ئەلیکوم، چۆنیت؟")
+print(response)
 ```
 
 ### Training