Instructions to use maxrajiv-buda/polar-orca with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maxrajiv-buda/polar-orca with Transformers:

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

pipe = pipeline("text-generation", model="maxrajiv-buda/polar-orca")
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("maxrajiv-buda/polar-orca")
model = AutoModelForCausalLM.from_pretrained("maxrajiv-buda/polar-orca", 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 maxrajiv-buda/polar-orca with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/maxrajiv-buda/polar-orca

SGLang

How to use maxrajiv-buda/polar-orca 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 "maxrajiv-buda/polar-orca" \
    --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": "maxrajiv-buda/polar-orca",
		"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 "maxrajiv-buda/polar-orca" \
        --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": "maxrajiv-buda/polar-orca",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use maxrajiv-buda/polar-orca with Docker Model Runner:
```
docker model run hf.co/maxrajiv-buda/polar-orca
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Polar Orca

Formerly IRA Dolphine · Built by Rajiv Buda · Base model: Qwen2.5-3B (unsloth/Qwen2.5-3B-Instruct-bnb-4bit)

I'm Polar Orca, built by Rajiv Buda to turn knowledge into opportunity, for everyone, everywhere.

Vision

Opportunity for everyone: make expert-level guidance on careers, business and tech free and easy to reach for anyone, not just people with connections.
Bridges between people: help companies, cultures and teams understand each other, across languages and borders.
Honest and humble: say what it knows, admit what it doesn't, and never make things up.
Always learning: get a little better with every conversation and every training run.
Built by one person, for many: show that one determined person with open tools can create AI that helps people around the world.

About

A LoRA fine-tune of Qwen2.5-3B-Instruct (4-bit, via Unsloth and TRL), trained on a free Colab T4. This repo was renamed from maxrajiv-buda/ira-dolphin; the old URL redirects here.

Developed by: Rajiv Buda (maxrajiv-buda)
License: apache-2.0
Finetuned from: unsloth/Qwen2.5-3B-Instruct-bnb-4bit
GGUF build: maxrajiv-buda/polar-orca-GGUF
Case study: https://rajivbuda.com/projects/polar-orca/
Training notebook: AI-Projects.ipynb

Limits: a small 3B model that can make mistakes. Evaluation so far is a held-out smoke test, not a benchmark. The weights reflect the last uploaded training run; the identity and vision data for the Polar Orca name live in the notebook.

Usage

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="maxrajiv-buda/polar-orca",
    max_seq_length=2048,
    load_in_4bit=True,
)
FastLanguageModel.for_inference(model)

messages = [{"role": "user", "content": "Give strategic advice for a small fitness studio facing competition from a big gym chain."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(out[0], skip_special_tokens=True))

With plain transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("maxrajiv-buda/polar-orca")
model = AutoModelForCausalLM.from_pretrained("maxrajiv-buda/polar-orca", device_map="auto")

Downloads last month: 270

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for maxrajiv-buda/polar-orca

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

unsloth/Qwen2.5-3B-Instruct-bnb-4bit

Finetuned

(190)

this model

Quantizations

1 model