Instructions to use prithivMLmods/Asterope-21-OpenR1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Asterope-21-OpenR1 with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Asterope-21-OpenR1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Asterope-21-OpenR1")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Asterope-21-OpenR1")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use prithivMLmods/Asterope-21-OpenR1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Asterope-21-OpenR1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Asterope-21-OpenR1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Asterope-21-OpenR1

SGLang

How to use prithivMLmods/Asterope-21-OpenR1 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 "prithivMLmods/Asterope-21-OpenR1" \
    --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": "prithivMLmods/Asterope-21-OpenR1",
		"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 "prithivMLmods/Asterope-21-OpenR1" \
        --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": "prithivMLmods/Asterope-21-OpenR1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Asterope-21-OpenR1 with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Asterope-21-OpenR1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Asterope-21-OpenR1

Asterope-21-OpenR1 is a distributed reinforcement learning (RL) fine-tuned model based on Qwen-1.5B, purpose-built to enhance coding proficiency, debugging accuracy, and step-by-step reasoning in software development tasks across multiple programming languages. Compact yet capable, it's ideal for intelligent coding assistants, developer tools, and embedded reasoning engines.

Key Features

Code-Centric Chain-of-Thought Reasoning
Optimized to generate structured, multi-step solutions for programming problems — including algorithm design, debugging, and code explanation — enabling developers to understand the "why" behind each step.
Distributed Reinforcement Learning Fine-Tuning
Trained with reinforcement learning across distributed environments to reinforce optimal coding strategies and accurate logical reasoning pathways.
Multilingual Programming Support
Supports various programming languages (e.g., Python, JavaScript, C++, Java, Go) and adapts to a wide range of development contexts from scripting to systems programming.
Lightweight, Developer-Ready (1.5B Parameters)
Designed for low-latency environments like IDE extensions, browser dev tools, and CLI bots, making it both fast and resource-efficient.

Quickstart with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Asterope-21-OpenR1"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Debug the following Python code:\ndef add(a, b):\n  return a + b\nprint(add(5))"
messages = [
    {"role": "system", "content": "You are a skilled coding assistant capable of reasoning step-by-step to solve software development tasks."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Intended Use

Code Debugging Assistants: Identifying, explaining, and fixing bugs with precision.
Educational Coding Tools: Helping users learn how and why code works, with rich step-by-step walkthroughs.
Multi-language Code Generation: Write clean, working code across languages and platforms.
Lightweight IDE Integration: Embed into editors, terminals, or web-based environments.

Limitations

Focused Domain:
Optimized for development workflows. May underperform in creative or non-technical tasks.
Model Scale:
Though efficient, complex multi-file or large-context debugging tasks may benefit from larger models.
RL Bias Toward Code Tasks:
Reinforcement learning favors coding reasoning paths — outputs for general-purpose Q&A may be limited.
Prompt Structure Matters:
More effective when inputs include structured error messages, full code context, or clear questions.