Instructions to use WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled with Transformers:

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

pipe = pipeline("text-generation", model="WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled")
model = AutoModelForCausalLM.from_pretrained("WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled

SGLang

How to use WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled 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 "WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled" \
    --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": "WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled",
		"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 "WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled" \
        --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": "WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled with Docker Model Runner:
```
docker model run hf.co/WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled
```

Gemini3.5-Code.Reasoner-2b-Distilled

Gemini3.5-Code.Reasoner-2b-Distilled is a highly efficient, reasoning-dense model tailored for advanced coding tasks, algorithmic problem-solving, and logical chain-of-thought workflows.

By applying a specialized Low-Rank Adaptation (LoRA) layer over CodeGemma 1.1 2B, this model infuses frontier-level reasoning mechanics into a compact, 2-billion parameter architecture. It bridges the gap between massive cloud-hosted models and local, edge-compute hardware.

Model Details

Developed by: WithinUsAI
Model Type: Causal Language Model (Fine-tuned / Knowledge Distilled)
Base Model: google/codegemma-1.1-2b
Architecture: GemmaForCausalLM (CodeGemma variant) + LoRA Adapters
License: Apache 2.0

Training & Dataset Recipe

The "Reasoner" capabilities of this model are distilled from a multi-source synthetic pipeline focusing on complex coding logic, algorithmic optimization, and step-by-step thinking patterns. The training mixture leverages approximately 100K+ high-quality reasoning examples across five core datasets:

Dataset Name	Source / Focus	Approx. Size
`WithinUsAI/GeminiPro3.2_max_distill_god_seed_25k`	High-quality frontier seed prompts for code generation.	~25k samples
`WithinUsAI/gemini_3.5_flash_distilled_25k`	Fast, iterative logical steps and multi-turn debugging data.	~25k samples
`WithinUsAI/Gemini_3.2_Pro_Distilled`	Heavy math logic, structural coding, and system design patterns.	Premium corpus
`WithinUsAI/codegemma_gemini_pro_32_distilled_25k`	Target-aligned distillation data optimized for the CodeGemma vocabulary.	~25k samples
`WithinUsAI/DEEPMIND_Alpha_Distilled`	Deep algorithmic competitive programming and math reasoning.	Premium corpus

Intended Use

Local Code Assistants: Ideal for IDE plugins requiring fast, low-latency code completion and instruction following.
Logical Chain-of-Thought: Designed to output its reasoning process before writing the final code block, minimizing syntax and logical errors.
Resource-Constrained Environments: Can easily be deployed on mobile devices, single-GPU setups, or local laptops using frameworks like vLLM, Ollama, or SGLang.

Quickstart Guide

Inference with Hugging Face Transformers

Because CodeGemma utilizes specialized tokens for coding workflows, it's recommended to structure your prompts cleanly to prompt the model's inner chain-of-thought.

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Prompt the model to think step-by-step before delivering code
prompt = """<bos>Analyze the problem and think step-by-step before writing any code.
Problem: Write a Python generator function that yields the Fibonacci sequence up to n elements.
Answer:"""

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.2)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))