Instructions to use jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4 with Transformers:

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

pipe = pipeline("text-generation", model="jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4")
model = AutoModelForCausalLM.from_pretrained("jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4

SGLang

How to use jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4 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 "jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4 with Docker Model Runner:
```
docker model run hf.co/jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4
```

SmolLM2-1.7B — Scheduled QAT (Linear Schedule)

This model was produced by Scheduled Quantization-Aware Training with a linear precision reduction schedule, targeting INT4 deployment on edge devices (Android, iOS, Raspberry Pi).

Important

This model is in bfloat16 — it is NOT quantized. QAT trains weights to be robust to quantization noise, but the actual quantization happens at export time. For the quantized GGUF versions ready for deployment, see:

jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-GGUF

Training Details

Parameter	Value
Base model	HuggingFaceTB/SmolLM2-1.7B
Method	Scheduled QAT (Linear bit-width reduction)
Training data	WikiText-103 (4000 sequences × 512 tokens)
Hardware	Kaggle TPU v5e-8 (8 cores)
Epochs	1
Effective batch size	64 (4 per-core × 2 grad accum × 8 cores)
Learning rate	2e-5 (cosine decay)
Optimizer	AdamW (weight_decay=0.01)
Training precision	bfloat16
Training time	~1150 seconds

Bit-Width Schedule

Phase	Epoch Range	Bit-width
Warmup	0.0 → 0.1	FP32 (no quantization noise)
Linear reduction	0.1 → 0.9	32 → 16 → 8 → 4 (gradual)
Stabilization	0.9 → 1.0	INT4 (final fine-tuning)

Results (WikiText-103 Test)

Metric	Value
Test loss	3.0392
Test perplexity	20.89

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4")

inputs = tokenizer("The future of AI is", return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Files

File	Description
`model.safetensors`	Model weights (bfloat16)
`config.json`	Model architecture config
`tokenizer.json`	Tokenizer
`results.json`	Training results (loss, perplexity)
`training_log.json`	Step-by-step training log

GGUF (quantized, for deployment): jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-GGUF
Base model: HuggingFaceTB/SmolLM2-1.7B

Citation

This model is part of a thesis on Scheduled Quantization-Aware Training for Small Language Models targeting edge deployment.

License

Apache 2.0 (same as base model)

Downloads last month: 10

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for jpcurada/SmolLM2-1.7B-Scheduled-QAT-Linear-INT4

Base model

HuggingFaceTB/SmolLM2-1.7B

Finetuned

(58)

this model

jpcurada
/

SmolLM2-1.7B-Scheduled-QAT-Linear-INT4