Upload NextStep-Coder-MoE LoRA adapter

README.md

@@ -0,0 +1,101 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+tags:
+- code
+- reasoning
+- chain-of-thought
+- lora
+- moe
+- fine-tuned
+base_model: Qwen/Qwen2.5-Coder-1.5B
+pipeline_tag: text-generation
+---
+
+# NextStep-Coder-MoE
+
+A high-performance tiny coding LLM with **Interleaved Thinking** capability for advanced reasoning and agentic workflows.
+
+## Model Description
+
+NextStep-Coder-MoE is a LoRA fine-tuned model based on Qwen2.5-Coder-1.5B, optimized for:
+- Chain-of-Thought reasoning with `<think>...</think>` tags
+- Multi-step coding tasks
+- Agentic workflows (plan → act → reflect)
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+# Load model
+base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B")
+model = PeftModel.from_pretrained(base_model, "OsamaBinLikhon/NextStep-Coder-MoE")
+tokenizer = AutoTokenizer.from_pretrained("OsamaBinLikhon/NextStep-Coder-MoE")
+
+# Generate
+prompt = "Write a Python function to check if a number is prime.\n<think>"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs[0]))
+```
+
+## Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| Base Model | Qwen/Qwen2.5-Coder-1.5B |
+| Method | LoRA (r=16, alpha=32) |
+| Trainable Params | 18.4M (1.18%) |
+| Precision | bf16 |
+| Framework | Transformers + PEFT |
+
+## Interleaved Thinking Format
+
+The model uses `<think>` tags to show reasoning:
+
+```
+User: Write a binary search function.
+
+Model: <think>
+I need to implement binary search on a sorted array.
+Key steps: find middle, compare, narrow search space.
+Edge case: empty array returns -1.
+</think>
+
+def binary_search(arr, target):
+    left, right = 0, len(arr) - 1
+    while left <= right:
+        mid = (left + right) // 2
+        if arr[mid] == target:
+            return mid
+        elif arr[mid] < target:
+            left = mid + 1
+        else:
+            right = mid - 1
+    return -1
+```
+
+## Intended Use
+
+- Code generation with step-by-step reasoning
+- Debugging and code review
+- Algorithm design and explanation
+- Educational coding assistance
+
+## Limitations
+
+- Best for Python, may vary for other languages
+- Requires `<think>` tag retention in conversation history
+- 2048 token context limit
+
+## Author
+
+**OsamaBinLikhon**
+
+## License
+
+Apache 2.0