Instructions to use arjhinety/onebee-gf-dpo-v1-scale with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arjhinety/onebee-gf-dpo-v1-scale with Transformers:

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

pipe = pipeline("image-text-to-text", model="arjhinety/onebee-gf-dpo-v1-scale")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("arjhinety/onebee-gf-dpo-v1-scale")
model = AutoModelForMultimodalLM.from_pretrained("arjhinety/onebee-gf-dpo-v1-scale", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arjhinety/onebee-gf-dpo-v1-scale with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arjhinety/onebee-gf-dpo-v1-scale"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arjhinety/onebee-gf-dpo-v1-scale",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/arjhinety/onebee-gf-dpo-v1-scale

SGLang

How to use arjhinety/onebee-gf-dpo-v1-scale 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 "arjhinety/onebee-gf-dpo-v1-scale" \
    --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": "arjhinety/onebee-gf-dpo-v1-scale",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "arjhinety/onebee-gf-dpo-v1-scale" \
        --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": "arjhinety/onebee-gf-dpo-v1-scale",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use arjhinety/onebee-gf-dpo-v1-scale with Docker Model Runner:
```
docker model run hf.co/arjhinety/onebee-gf-dpo-v1-scale
```

onebee-gf-dpo-v1-scale

Proper-scale LoRA DPO checkpoint on top of sft-v1 (2049 preference pairs) — pre-distillation, strongest preference-optimization signal in this project.

Model Overview

Proper-scale DPO checkpoint on top of sft-v1 — 2049 preference pairs (~10x dpo-v0's scale), 1 epoch. Strongest and cleanest preference-optimization signal observed across every run in this project (24.7pp pairwise win-rate gap). Superseded by onebee-gf-distill-v1 (adds on-policy distillation on top of this checkpoint) as the current best overall, but this remains the pre-distillation baseline used in that comparison, and the checkpoint the published GGUF quantizations are built from.

GGUF quantizations available: this checkpoint is also published as [quantizations (F16 reference plus 12 quant levels)](https://huggingface.co/arjhinety/onebee-gf-dpo-v1-scale-gguf) ((F16 reference plus 12 quant levels down to Q2_K, plus vision projector)) for llama.cpp-based on-device inference.

Model Details

Property	Details
Model	`onebee-gf-dpo-v1-scale`
Parameters	~2B effective (base) + LoRA rank 16 adapter
Architecture	Gemma4 (multimodal, text + vision)
Base Model	`google/gemma-4-E2B-it`
Language	English
Context Length	131,072 tokens (inherited from base model)
Training Method	LoRA DPO, 1 epoch, 2049 preference pairs, chained off sft-v1
License	Apache-2.0 (inherited from base model)

Intended Use

As a base for distillation or quantization; as a strong standalone companion checkpoint if distillation-specific behavior is not desired.

Out-of-Scope Use

Not evaluated or intended for: safety-critical decisions, medical/legal/financial advice, or any deployment where a wrong or overconfident answer causes real harm. This is a research artifact from an open-source project studying post-training and memory architecture on small models — see the project README for the full research framing before using it in any production context.

Capabilities

Companion-persona conversational responses with strong preference alignment
Preference alignment: 45.7% vs 21.0% pairwise win-rate over SFT-only (24.7pp gap, 105 probes)

No full-PMB pra_lenient/UAR measurement exists for this checkpoint — it is evaluated pairwise only. The 70.0% UAR figure that appeared here in earlier revisions belongs to the SFT-v1+memory system, not to DPO. See reports/ERRATA.md.

Quick Start

Installation

pip install transformers torch

Usage

from transformers import AutoModelForCausalLM, AutoProcessor

model = AutoModelForCausalLM.from_pretrained("arjhinety/onebee-gf-dpo-v1-scale")
processor = AutoProcessor.from_pretrained("arjhinety/onebee-gf-dpo-v1-scale")

messages = [
    {"role": "system", "content": "You are a warm AI companion who remembers this user."},
    {"role": "user", "content": "What conference did I say I was attending?"},
]
inputs = processor.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
output = model.generate(**inputs, max_new_tokens=128)
print(processor.decode(output[0], skip_special_tokens=True))

Evaluation

Scored against PMB (Personalized Memory Benchmark), 688 adversarial probes across 8 categories, with an LLM judge under dual-order (position-bias-controlled) scoring plus a rule-based abstention detector.

System	pairwise win-rate	UAR
dpo-v1-scale	45.7% vs 21.0% (24.7pp gap)	70.0%

Full methodology, all numbers, and honest limitations: docs/proper_scale_results.md.

Limitations

Single seed/run at this data scale. See onebee-gf-distill-v1 for the further-improved current-best checkpoint.

This project reports negative/inconclusive results as honestly as positive ones — read the linked docs before assuming any number here is a clean win.

Other Checkpoints From This Project

Repo	Description
onebee-gf-sft-v0	Day 4 v0 SFT (202 examples)
onebee-gf-sft-v1	Proper-scale SFT (2232 examples)
onebee-gf-dpo-v0	Week 2 DPO v0 (200 pairs)
onebee-gf-dpo-v1-4epoch	DPO overfitting experiment
onebee-gf-dpo-v1-scale	Proper-scale DPO, pre-distillation
onebee-gf-distill-v1	SFT+DPO+distillation — current best overall
onebee-gf-dpo-v1-scale-gguf	GGUF quantizations

Citation

@software{small_mind_companion,
  title  = {small-mind-companion: Post-training and cognitive architecture for a small multimodal companion LLM},
  author = {arjhinety},
  year   = {2026},
  url    = {https://github.com/arjhinety/small-mind-companion}
}