Instructions to use celebibasar/DroidSenior-7B-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use celebibasar/DroidSenior-7B-v3 with Transformers:

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

pipe = pipeline("text-generation", model="celebibasar/DroidSenior-7B-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("celebibasar/DroidSenior-7B-v3")
model = AutoModelForCausalLM.from_pretrained("celebibasar/DroidSenior-7B-v3", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use celebibasar/DroidSenior-7B-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "celebibasar/DroidSenior-7B-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "celebibasar/DroidSenior-7B-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/celebibasar/DroidSenior-7B-v3

SGLang

How to use celebibasar/DroidSenior-7B-v3 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 "celebibasar/DroidSenior-7B-v3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "celebibasar/DroidSenior-7B-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "celebibasar/DroidSenior-7B-v3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "celebibasar/DroidSenior-7B-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use celebibasar/DroidSenior-7B-v3 with Docker Model Runner:
```
docker model run hf.co/celebibasar/DroidSenior-7B-v3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DroidSenior-7B v3

An Android and Kotlin coding model. Continues from DroidSenior v1/v2, whose training data included JetBrains/KExercises (CC-BY-NC-SA-4.0). Check those terms before commercial use.

System prompt

You are DroidSenior, a staff-level Android engineer. Write idiomatic, modern Kotlin (Jetpack Compose, Coroutines/Flow, Hilt, Room) following the official Android architecture guidance. Explain key design decisions and trade-offs briefly, never use deprecated APIs, avoid over-engineering, and include tests when they add value. Answer in the user's language.

Training

SFT: 6026 examples, LoRA r=32, loss on assistant tokens only.
DPO: 1208 compiler-verified pairs (the rejected answer failed to compile), beta=0.1.
Questions from the evaluation split were removed from training data.

Evaluation

All models used the same system prompt and deterministic generation. Rates show 95% bootstrap intervals.

model	Android compile rate	Kotlin HumanEval pass rate	legacy API rate
base	2.6% (0%-6%)	62.1% (55%-70%)	40%
v1	5.1% (1%-10%)	64.0% (57%-71%)	3%
v2	3.8% (0%-9%)	64.6% (57%-72%)	4%
sft_r2	20.5% (12%-29%)	67.7% (60%-75%)	0%
dpo_r2	20.5% (12%-29%)	67.7% (61%-75%)	0%

Android compile rate: answers to 78 held-out questions, each asking for self-contained code, compiled with :app:compileDebugKotlin in a fixed template project, without KSP. It measures compilation, not behavior.
Kotlin HumanEval: 161 tasks from JetBrains/Kotlin_HumanEval.
Selected model: dpo_r2. Android difference against v1: +15.4% (95% CI +6.4% to +24.4%).

Q4_K_M GGUF: 4.68 GB, CPU speed 7.3 tokens/s on Colab.

Limitations

Generated code can still be wrong. Review it before use.
Recent APIs may be missing.
These are self-run tests, not an official Android Bench result.

Downloads last month: 14

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for celebibasar/DroidSenior-7B-v3

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Finetuned

celebibasar/DroidSenior-7B

Finetuned

(1)

this model

Quantizations

2 models

celebibasar
/

DroidSenior-7B-v3

DroidSenior-7B v3

System prompt

Training

Evaluation

Limitations

Model tree for celebibasar/DroidSenior-7B-v3

Datasets used to train celebibasar/DroidSenior-7B-v3