Instructions to use CountingSheep/vev-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CountingSheep/vev-9b with Transformers:

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

pipe = pipeline("image-text-to-text", model="CountingSheep/vev-9b")
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)

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

processor = AutoProcessor.from_pretrained("CountingSheep/vev-9b")
model = AutoModelForMultimodalLM.from_pretrained("CountingSheep/vev-9b", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CountingSheep/vev-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CountingSheep/vev-9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CountingSheep/vev-9b",
		"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/CountingSheep/vev-9b

SGLang

How to use CountingSheep/vev-9b 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 "CountingSheep/vev-9b" \
    --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": "CountingSheep/vev-9b",
		"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 "CountingSheep/vev-9b" \
        --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": "CountingSheep/vev-9b",
		"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 CountingSheep/vev-9b with Docker Model Runner:
```
docker model run hf.co/CountingSheep/vev-9b
```

vev-9b

File size: 1,112 Bytes

1e6afb7

{
  "base_model": "Qwen/Qwen3.5-9B",
  "vev_version": "0.1.0",
  "train_args": {
    "build": "v1-research",
    "base": "Qwen/Qwen3.5-9B",
    "out": "train",
    "limit": 100000,
    "sources": null,
    "source_weights": null,
    "max_steps": 2500,
    "lr": 5e-05,
    "head_lr": 0.0,
    "lora_r": 16,
    "lora_alpha": 0,
    "lora_dropout": 0.05,
    "lora_targets": "all",
    "dp": 256,
    "prior": true,
    "anchor_kl": 0.3,
    "anchor_build": "anchor-v3",
    "anchor_weight": 2.0,
    "anchor_sym": false,
    "consistency": 0.0,
    "consistency_frac": 0.5,
    "micro_tokens": 16384,
    "accum": 4,
    "max_q": 4,
    "max_row_tokens": 4096,
    "max_pixels": 1048576,
    "brier": 0.1,
    "score_w": 0.05,
    "weight_decay": 0.0,
    "grad_clip": 1.0,
    "warmup_pct": 0.1,
    "no_augment": false,
    "no_gradient_checkpointing": false,
    "dtype": "bf16",
    "attn": null,
    "workers": 8,
    "eval_every": 250,
    "eval_rows": 1000,
    "eval_records": 2000,
    "save_every": 250,
    "log_every": 10,
    "seed": 0,
    "resume": null,
    "device": "cuda"
  },
  "base": "."
}