Instructions to use rty813/d1-3B-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rty813/d1-3B-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="rty813/d1-3B-bf16", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("rty813/d1-3B-bf16", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("rty813/d1-3B-bf16", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rty813/d1-3B-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rty813/d1-3B-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rty813/d1-3B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rty813/d1-3B-bf16

SGLang

How to use rty813/d1-3B-bf16 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 "rty813/d1-3B-bf16" \
    --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": "rty813/d1-3B-bf16",
		"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 "rty813/d1-3B-bf16" \
        --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": "rty813/d1-3B-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rty813/d1-3B-bf16 with Docker Model Runner:
```
docker model run hf.co/rty813/d1-3B-bf16
```

d1-3B-bf16 (bf16)

Full-precision (bf16) PyTorch port of LiquidAI/d1-3B, for vLLM / TGI / Xinference / transformers users who don't want the GGUF quant.

Format: pytorch_model.bin (bf16). safetensors conversion in progress.
Architecture: identical to the original — drop-in for AutoModelForCausalLM.from_pretrained("rty813/d1-3B-bf16").
Also loads in vLLM (vllm serve rty813/d1-3B-bf16) and Xinference (search "d1-3B").

Original model card:

library_name: transformers license: other license_name: lfm1.0 license_link: LICENSE language: - ar - zh - en - fr - de - hi - id - it - ja - ko - pl - pt - ru - es - th - vi pipeline_tag: image-text-to-text base_model: LiquidAI/LFM2.5-VL-3B tags: - liquid - lfm2.5 - edge - decision - classification - calibration - system-one - multimodal - decision-model

Try LFM • Docs • Discord

d1-3B

d1-3B is a 3B parameter decision model built on LFM2.5-VL-3B. You give it a state (text, JSON, images, or a mix) and a set of questions. It returns calibrated, typed answers in one forward pass with zero output tokens.

Best decision model under 10B on the Decision Index 0.2.1: 48.57, ahead of every 4B and 9B model and of Decider 35B-A3B (47.11).
Multimodal: images and text in the same state. It scores 74.1 on

Downloads last month: 50

Model tree for rty813/d1-3B-bf16

Base model

LiquidAI/LFM2.5-2.6B-Base

Finetuned

LiquidAI/LFM2.5-VL-3B

Finetuned

LiquidAI/d1-3B

Finetuned

(7)

this model