Instructions to use everettjf/ezjev-4b-s3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use everettjf/ezjev-4b-s3 with Transformers:

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

pipe = pipeline("image-text-to-text", model="everettjf/ezjev-4b-s3")
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("everettjf/ezjev-4b-s3")
model = AutoModelForMultimodalLM.from_pretrained("everettjf/ezjev-4b-s3", 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 everettjf/ezjev-4b-s3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "everettjf/ezjev-4b-s3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "everettjf/ezjev-4b-s3",
		"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/everettjf/ezjev-4b-s3

SGLang

How to use everettjf/ezjev-4b-s3 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 "everettjf/ezjev-4b-s3" \
    --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": "everettjf/ezjev-4b-s3",
		"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 "everettjf/ezjev-4b-s3" \
        --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": "everettjf/ezjev-4b-s3",
		"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 everettjf/ezjev-4b-s3 with Docker Model Runner:
```
docker model run hf.co/everettjf/ezjev-4b-s3
```

ezjev-4b-s3

File size: 2,544 Bytes

3a54167

{
 "base_model": "everettjf/ezjev-4b-s2",
 "temperature": 1.34,
 "prompt": "llm2jev --prompt chat",
 "dev_before": {
  "acc": 0.8629690048939641,
  "nll": 0.33060150389515075,
  "brier": 0.18319715428060893,
  "per_src": {
   "acos_train": 0.967,
   "ag_news": 1.0,
   "anli_train": 0.797,
   "aqua": 0.389,
   "arc_train": 0.96,
   "banking77_train": 0.8,
   "boolq": 0.885,
   "clinc_train": 0.957,
   "contractnli_train": 1.0,
   "csqa": 0.76,
   "dbpedia": 1.0,
   "emotion": 0.429,
   "esci_train": 0.55,
   "gen_bbh": 0.821,
   "gen_cladder": 0.921,
   "gen_crux": 0.892,
   "gen_gsm": 1.0,
   "glaive_tools": 0.833,
   "gsm8k_fmt": 0.897,
   "hellaswag": 0.889,
   "hh_rlhf": 0.6,
   "hotpot_train": 0.9,
   "humicroedit_train": 0.545,
   "irony": 0.759,
   "isarcasm_train": 0.849,
   "massive_train": 0.9,
   "mmlu_aux": 0.907,
   "mnli": 0.85,
   "newyorker_train": 0.8,
   "nli4ct_train": 0.789,
   "obqa": 0.875,
   "qasc": 0.643,
   "qnli_rank": 0.994,
   "ragtruth_train": 0.87,
   "sata_numbers": 1.0,
   "sata_sciq": 0.982,
   "sciq": 1.0,
   "sgd_train": 0.973,
   "sharc": 0.739,
   "shp": 0.64,
   "snli": 0.875,
   "sst5": 0.3,
   "tools_apibank": 0.882,
   "tools_bfcl": 0.95,
   "tools_rank": 1.0,
   "vast_train": 0.683,
   "when2call_train": 0.976,
   "winogrande": 0.817,
   "yahoo": 0.5
  }
 },
 "dev_after": {
  "acc": 0.8656878738444806,
  "nll": 0.3317063585519117,
  "brier": 0.18388888261965453,
  "per_src": {
   "acos_train": 0.967,
   "ag_news": 1.0,
   "anli_train": 0.797,
   "aqua": 0.389,
   "arc_train": 0.96,
   "banking77_train": 0.85,
   "boolq": 0.885,
   "clinc_train": 0.971,
   "contractnli_train": 1.0,
   "csqa": 0.76,
   "dbpedia": 1.0,
   "emotion": 0.571,
   "esci_train": 0.575,
   "gen_bbh": 0.885,
   "gen_cladder": 0.921,
   "gen_crux": 0.919,
   "gen_gsm": 0.913,
   "glaive_tools": 0.833,
   "gsm8k_fmt": 0.897,
   "hellaswag": 0.867,
   "hh_rlhf": 0.55,
   "hotpot_train": 0.875,
   "humicroedit_train": 0.773,
   "irony": 0.759,
   "isarcasm_train": 0.868,
   "massive_train": 0.867,
   "mmlu_aux": 0.907,
   "mnli": 0.85,
   "newyorker_train": 0.84,
   "nli4ct_train": 0.789,
   "obqa": 0.875,
   "qasc": 0.643,
   "qnli_rank": 0.994,
   "ragtruth_train": 0.804,
   "sata_numbers": 1.0,
   "sata_sciq": 1.0,
   "sciq": 1.0,
   "sgd_train": 0.946,
   "sharc": 0.739,
   "shp": 0.56,
   "snli": 0.75,
   "sst5": 0.3,
   "tools_apibank": 0.882,
   "tools_bfcl": 0.95,
   "tools_rank": 1.0,
   "vast_train": 0.707,
   "when2call_train": 1.0,
   "winogrande": 0.8,
   "yahoo": 0.5
  }
 }
}