Instructions to use OsamaBinLikhon/NextStep-Coder-MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsamaBinLikhon/NextStep-Coder-MoE with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("distilgpt2")
model = PeftModel.from_pretrained(base_model, "OsamaBinLikhon/NextStep-Coder-MoE")

Transformers

How to use OsamaBinLikhon/NextStep-Coder-MoE with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="OsamaBinLikhon/NextStep-Coder-MoE")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("OsamaBinLikhon/NextStep-Coder-MoE", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OsamaBinLikhon/NextStep-Coder-MoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OsamaBinLikhon/NextStep-Coder-MoE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OsamaBinLikhon/NextStep-Coder-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OsamaBinLikhon/NextStep-Coder-MoE

SGLang

How to use OsamaBinLikhon/NextStep-Coder-MoE with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OsamaBinLikhon/NextStep-Coder-MoE" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OsamaBinLikhon/NextStep-Coder-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OsamaBinLikhon/NextStep-Coder-MoE" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OsamaBinLikhon/NextStep-Coder-MoE",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OsamaBinLikhon/NextStep-Coder-MoE with Docker Model Runner:
```
docker model run hf.co/OsamaBinLikhon/NextStep-Coder-MoE
```

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

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

Framework versions

PEFT 0.18.0

Downloads last month: -

Model tree for OsamaBinLikhon/NextStep-Coder-MoE

Base model

distilbert/distilgpt2

Adapter

(79)

this model