Instructions to use kenpeter123/small-1b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kenpeter123/small-1b-sft with Transformers:

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

pipe = pipeline("text-generation", model="kenpeter123/small-1b-sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kenpeter123/small-1b-sft")
model = AutoModelForCausalLM.from_pretrained("kenpeter123/small-1b-sft", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kenpeter123/small-1b-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kenpeter123/small-1b-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kenpeter123/small-1b-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kenpeter123/small-1b-sft

SGLang

How to use kenpeter123/small-1b-sft 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 "kenpeter123/small-1b-sft" \
    --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": "kenpeter123/small-1b-sft",
		"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 "kenpeter123/small-1b-sft" \
        --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": "kenpeter123/small-1b-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kenpeter123/small-1b-sft with Docker Model Runner:
```
docker model run hf.co/kenpeter123/small-1b-sft
```

Small-1B SFT Model

SFT (supervised fine-tuned) model — 1B Transformer++ base (kenpeter123/small-1b-pretrain) fine-tuned on quality-filtered mixed instruction shards (513 verified-code + 2500 generated), 8-bit Adam optimizer, stage-isolated checkpoint.

Spec	Value
Params	1,031,898,624 (~1.03B)
Hidden	1536 · 32 layers · 12 attn heads · 4 KV (GQA) · head_dim 128
FFN	4608 SwiGLU
Seq len	2048 (train) / 8192 (config)
Vocab	49152 (SmolLM2-135M tokenizer, BPE)
Optimizer	bitsandbytes Adam8bit, bf16, cosine LR
SFT loss	20.5897 @ step 1000

Raw training checkpoint included as sft_best.pt (model_state_dict + optimizer_state_dict).

Downloads last month: 247

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for kenpeter123/small-1b-sft

Base model

HuggingFaceTB/SmolLM2-135M

Finetuned

kenpeter123/small-1b-pretrain

Finetuned

(1)

this model

Finetunes

1 model