Instructions to use auryn-macmillan/boostedv1-ilv9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use auryn-macmillan/boostedv1-ilv9 with Transformers:

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

pipe = pipeline("text-generation", model="auryn-macmillan/boostedv1-ilv9")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("auryn-macmillan/boostedv1-ilv9")
model = AutoModelForCausalLM.from_pretrained("auryn-macmillan/boostedv1-ilv9", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use auryn-macmillan/boostedv1-ilv9 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "auryn-macmillan/boostedv1-ilv9"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "auryn-macmillan/boostedv1-ilv9",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/auryn-macmillan/boostedv1-ilv9

SGLang

How to use auryn-macmillan/boostedv1-ilv9 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 "auryn-macmillan/boostedv1-ilv9" \
    --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": "auryn-macmillan/boostedv1-ilv9",
		"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 "auryn-macmillan/boostedv1-ilv9" \
        --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": "auryn-macmillan/boostedv1-ilv9",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use auryn-macmillan/boostedv1-ilv9 with Docker Model Runner:
```
docker model run hf.co/auryn-macmillan/boostedv1-ilv9
```

BoostedV1-ILv9

Iterative-Learning (IL v9) version of BoostedV1: continued LoRA training of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Built from the BoostedV1 Phase-1 model (400 MLX steps + 550 continuation steps) plus 3 rounds of IL v9 self-improvement (generate -> verify -> self-audit -> train on filtered data).

Training

Base: BoostedV1 Phase-1 (DeepSeek-R1-Distill-Qwen-1.5B + LoRA r=8)
IL v9: 3 rounds, each generating 600 candidate solutions, externally verifying, model self-auditing (threshold 5/10), then training 100 steps on 52-65 high-quality examples per round
Best round: round_001 (merged here)

Evaluation

Benchmark	BoostedV1 (phase-1)	BoostedV1-ILv9
GSM8K	46.0%	46.5%
HumanEval (pass@1)	7.3%	11.0%

The IL v9 loop produced the largest gains on code generation (HumanEval pass@1 7.3% -> 11.0%).

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('auryn-macmillan/boostedv1-ilv9') tok = AutoTokenizer.from_pretrained('auryn-macmillan/boostedv1-ilv9') inputs = tok('Write Python to check if a number is prime.', return_tensors='pt') out = model.generate(**inputs, max_new_tokens=256) print(tok.decode(out[0]))

Notes

Standard Qwen2 architecture, no custom code, no trust_remote_code needed.
Trained in an isolated container; repo contains no training code or data.

Downloads last month: 334

Safetensors

Model size

2B params

Tensor type

BF16