Update README.md

1) return_full_text=False returns only generated part of text. Changes provide the same result.
Source:
https://huggingface.co/docs/transformers/main_classes/pipelines#transformers.TextGenerationPipeline.example
2) print(prompt) in test_inference provides some misunderstandings
3) typo in Колмогоров

README.md

@@ -27,13 +27,12 @@ from transformers import  AutoTokenizer, pipeline
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 prompts = [
     "В чем разница между фруктом и овощем?",
-    "Годы жизни колмагорова?"]
+    "Годы жизни колмогорова?"]
 
 def test_inference(prompt):
     prompt = pipe.tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True)
-    print(prompt)
-    outputs = pipe(prompt, max_new_tokens=512, do_sample=True, num_beams=1, temperature=0.25, top_k=50, top_p=0.98, eos_token_id=79097)
-    return outputs[0]['generated_text'][len(prompt):].strip()
+    outputs = pipe(prompt, max_new_tokens=512, return_full_text=False, do_sample=True, num_beams=1, temperature=0.25, top_k=50, top_p=0.98, eos_token_id=79097)
+    return outputs[0]['generated_text'].strip()
 
 
 for prompt in prompts: