Instructions to use yesenb/unc-7d2e2656 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yesenb/unc-7d2e2656 with Transformers:

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

pipe = pipeline("text-generation", model="yesenb/unc-7d2e2656")
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("yesenb/unc-7d2e2656")
model = AutoModelForMultimodalLM.from_pretrained("yesenb/unc-7d2e2656", 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 yesenb/unc-7d2e2656 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yesenb/unc-7d2e2656"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yesenb/unc-7d2e2656",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yesenb/unc-7d2e2656

SGLang

How to use yesenb/unc-7d2e2656 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 "yesenb/unc-7d2e2656" \
    --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": "yesenb/unc-7d2e2656",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "yesenb/unc-7d2e2656" \
        --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": "yesenb/unc-7d2e2656",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yesenb/unc-7d2e2656 with Docker Model Runner:
```
docker model run hf.co/yesenb/unc-7d2e2656
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Affine R334 — marsplan Online-DPO-long (merged)

LoRA-merged Online-DPO (β=0.1 α=32 r=16 G=4 lr=5e-6 temp=1.2 max_steps=300 FORCE_PREFIX) from live reign-22 king marsplan0624/affine-5gedzafcvg-queen@556d02a2.

Local n80 vs marsplan: margin=+0.01182 SE=0.00484 z=2.445 clears max(2·SE, δ=0.002); median_len_z=217; B pass=0.468. Stage-5 candidate.

Downloads last month: -

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for yesenb/unc-7d2e2656

Base model

marsplan0624/affine-5gedzafcvg-queen

Finetuned

(6)

this model