Update README.md

README.md

@@ -6,7 +6,6 @@ language:
 - en
 base_model:
 - unsloth/phi-4-reasoning
-new_version: SkyAsl/Rust-Master-thinking
 pipeline_tag: text-generation
 library_name: transformers
 tags:
@@ -58,13 +57,13 @@ import torch
 model_id = "SkyAsl/Rust-Master-thinking"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
+model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")
 model.eval()
 
 prompt = "Explain why Rust ownership prevents data races."
 
 input_text = (
-    f"<|user|>\n{test_data[0]['prompt']}\n"
+    f"<|user|>\n{prompt}\n"
     f"<|assistant|>\n<think>\n"
 )
 
@@ -73,7 +72,7 @@ inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
 with torch.no_grad():
     output = model.generate(
         **inputs,
-        max_new_tokens=500,
+        max_new_tokens=3000,      
         temperature=0.7,
         top_p=0.9,
         do_sample=True,
@@ -127,16 +126,6 @@ Includes:
 This dataset improves the model's ability to produce structured and
 accurate explanations for Rust programming tasks.
 
-## 🔍 Notes on Reasoning Tags
-
-This model preserves **hidden reasoning structure**:
-
--   `<think>` content is **internal chain-of-thought**
--   The final output is **placed after the reasoning block**
-
-⚠️ Users should NOT expect the `<think>` content to be revealed; the
-model is aligned to hide reasoning by default.
-
 ## ✨ Acknowledgements
 
 -   **Unsloth** for optimized model training