Instructions to use majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit with Transformers:

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

pipe = pipeline("text-generation", model="majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit")
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("majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit")
model = AutoModelForCausalLM.from_pretrained("majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit", 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 majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit

SGLang

How to use majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit 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 "majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit" \
    --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": "majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit",
		"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 "majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit" \
        --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": "majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit with Docker Model Runner:
```
docker model run hf.co/majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit
```

SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit

Weight-quantized via QuadRotor-Full at 4 bits.

Smoke results (WikiText-2, seq_len 2048, MPS)

Variant	Perplexity	Δ vs BF16
BF16 (upstream)	8.9391	—
Affine 4-bit	11.0134	+2.07 (+23 %)
QuadRotor-Full 4-bit	11.0197	+2.08 (+23 %)

Random Haar quaternions without calibration are essentially identical to plain affine 4-bit on this model (Δ +0.006). See the source repo for the consolidated picture and next-step recommendations.

Algorithm

Per group of 64 weight elements:

Split norm ρ = ‖x‖₂ from direction x̄ = x/ρ
Reshape x̄ into 16 blocks of 4 coordinates
Sample 16 pairs of unit quaternions from a per-tensor seed (SHA-256 of tensor name → 32-bit seed → Haar-on-S³)
Apply T(v) = q_L · v · q̄_R per block
Group-wise affine 4-bit quantize the rotated coordinates

Loading

import json, torch
from pathlib import Path
from huggingface_hub import snapshot_download
from safetensors.torch import load_file
from quadrotor.quantize import QuadRotorConfig
from quadrotor.state_dict import decode_state_dict

p = Path(snapshot_download("majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit"))
sidecar = json.loads((p / "quadrotor.json").read_text())
cfg = QuadRotorConfig(variant=sidecar["variant"], bits=sidecar["bits"], group_size=sidecar["group_size"])
state = load_file(str(p / "model.safetensors"))
restored = decode_state_dict(state, cfg, sidecar)

Source

Algorithm + tooling: github.com/ajentik/quadrotor
Base model: HuggingFaceTB/SmolLM2-1.7B-Instruct

License

Apache 2.0 (inherited from base model).

Downloads last month: 9

Safetensors

Model size

2B params

Tensor type

F32

BF16

Model tree for majentik/SmolLM2-1.7B-Instruct-QuadRotor-Full-4bit

Base model

HuggingFaceTB/SmolLM2-1.7B

Quantized

HuggingFaceTB/SmolLM2-1.7B-Instruct

Finetuned

(166)

this model