Update README.md

README.md

@@ -163,27 +163,25 @@ datasets:
 
   You can use it with a script
 
-  if do_run_lora_model:
-    if is_own:
-      model, tokenizer = FastLanguageModel.from_pretrained(
-          model_name="CineAI/Llama32-3B-CoT",
-          max_seq_length=max_length,
-          dtype=dtype,
-          load_in_4bit=load_in_4bit
-      )
-  
-      FastLanguageModel.for_inference(model)
-  
-    inputs = tokenizer.apply_chat_template(
-        message,
-        tokenize = True,
-        add_generation_prompt = True, # Must add for generation
-        return_tensors = "pt",
-    ).to(device)
-  
-    text_streamer = TextStreamer(tokenizer, skip_prompt = True)
-    _ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = max_new_tokens,
-                      use_cache = True, temperature = temperature, min_p = min_p)
+  model, tokenizer = FastLanguageModel.from_pretrained(
+        model_name="CineAI/Llama32-3B-CoT",
+        max_seq_length=max_length,
+        dtype=dtype,
+        load_in_4bit=load_in_4bit
+    )
+
+  FastLanguageModel.for_inference(model)
+
+  inputs = tokenizer.apply_chat_template(
+      message,
+      tokenize = True,
+      add_generation_prompt = True, # Must add for generation
+      return_tensors = "pt",
+  ).to(device)
+
+  text_streamer = TextStreamer(tokenizer, skip_prompt = True)
+  _ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = max_new_tokens,
+                    use_cache = True, temperature = temperature, min_p = min_p)
 
 # Uploaded  model