Instructions to use prithivMLmods/Procyon-1.5B-Qwen2-Theorem with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Procyon-1.5B-Qwen2-Theorem with Transformers:

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

pipe = pipeline("text-generation", model="prithivMLmods/Procyon-1.5B-Qwen2-Theorem")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Procyon-1.5B-Qwen2-Theorem")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Procyon-1.5B-Qwen2-Theorem")
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 Settings

vLLM

How to use prithivMLmods/Procyon-1.5B-Qwen2-Theorem with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Procyon-1.5B-Qwen2-Theorem"
# 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/Procyon-1.5B-Qwen2-Theorem",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Procyon-1.5B-Qwen2-Theorem

SGLang

How to use prithivMLmods/Procyon-1.5B-Qwen2-Theorem 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/Procyon-1.5B-Qwen2-Theorem" \
    --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/Procyon-1.5B-Qwen2-Theorem",
		"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/Procyon-1.5B-Qwen2-Theorem" \
        --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/Procyon-1.5B-Qwen2-Theorem",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prithivMLmods/Procyon-1.5B-Qwen2-Theorem with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Procyon-1.5B-Qwen2-Theorem
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Procyon-1.5B-Qwen2-Theorem

Procyon-1.5B-Qwen2-Theorem is an experimental theorem explanation model fine-tuned on Qwen2-1.5B. Specially crafted for mathematical theorem understanding, structured concept breakdowns, and non-reasoning based explanation tasks, it targets domains where clarity and formal structure take precedence over freeform reasoning.

GGUF: https://huggingface.co/prithivMLmods/Procyon-1.5B-Qwen2-Theorem-GGUF

Key Features

Mathematical Theorem Explanation Designed to deliver structured, formal, and accessible explanations of theorems across pure and applied mathematics, including areas such as algebra, calculus, topology, and number theory.
Concept Breakdown without Deep Reasoning Focuses on clarity over inference, offering non-reasoning-based breakdowns suitable for educational tools, step-by-step formal writing, and documentation-heavy workflows.
Concise and Interpretable Output Outputs content that aligns with pedagogical clarity: definitions, hypotheses, conclusions, and related implications—all in clean, human-readable structure.
Multi-Format Support Capable of generating content in formats such as LaTeX, Markdown, JSON (structured concept trees), and plain text, suitable for academic publishing and automated knowledge bases.
Lightweight and Efficient With a 1.5B parameter footprint, it is ideal for deployment on edge devices, local academic tools, and integrated learning platforms, offering quick responses without heavy compute demands.

Quickstart with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Procyon-1.5B-Qwen2-Theorem"

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

prompt = "Explain the Fundamental Theorem of Calculus in simple terms with hypotheses and conclusion."

messages = [
    {"role": "system", "content": "You are an assistant skilled at explaining mathematical theorems in a structured and simple format."},
    {"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]
print(response)