Update README.md

README.md

@@ -8,6 +8,7 @@ tags:
 - mistral
 - chatml
 - axolotl
+- kpo
 prompt_template: <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|>
   <|im_start|>assistant
 model-index:
@@ -73,21 +74,17 @@ gen = GenerationConfig(
     eos_token_id=tokenizer.convert_tokens_to_ids("<|im_end|>")
 )
 
+streamer = TextStreamer(tokenizer, skip_prompt=True)
+
 messages = [
     {"role": "system", "content": "Sei un assistente utile."},
     {"role": "user", "content": "{prompt}"}
 ]
 
-with torch.no_grad(), torch.backends.cuda.sdp_kernel(
-    enable_flash=True, 
-    enable_math=False,
-    enable_mem_efficient=False
-):
+with torch.no_grad():
     temp = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
     inputs = tokenizer(temp, return_tensors="pt").to("cuda")
 
-    streamer = TextStreamer(tokenizer, skip_prompt=True)
-
     _ = model.generate(
         **inputs,
         streamer=streamer,