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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kenpeter123/small-1b-dpo"
# 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-dpo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

Small-1B DPO Model

DPO (Direct Preference Optimization) model — 1B Transformer++ base, post-trained on top of SFT (kenpeter123/small-1b-sft) using preference pairs. Reference model = policy at init (standard DPO from the SFT anchor). 8-bit Adam, bf16, 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)
DPO	steps 300 · lr 1e-05 · β 0.1 · sigmoid loss
Optimizer	bitsandbytes Adam8bit, bf16

Preference pairs: raw problem prompt (chosen = gold correct solution, rejected = SFT model's wrong/echo generation). Raw training checkpoint included as dpo_best.pt (model_state_dict only, bf16).

Downloads last month: 272

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for kenpeter123/small-1b-dpo

Base model

HuggingFaceTB/SmolLM2-135M

Finetuned

kenpeter123/small-1b-pretrain

Finetuned

kenpeter123/small-1b-sft

Finetuned

(1)

this model