142-caphe-5HdchXe

Instructions to use penva/142-caphe-5HdchXe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use penva/142-caphe-5HdchXe with Transformers:

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

pipe = pipeline("image-text-to-text", model="penva/142-caphe-5HdchXe")
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("penva/142-caphe-5HdchXe")
model = AutoModelForMultimodalLM.from_pretrained("penva/142-caphe-5HdchXe")
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 penva/142-caphe-5HdchXe with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "penva/142-caphe-5HdchXe"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "penva/142-caphe-5HdchXe",
		"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/penva/142-caphe-5HdchXe

SGLang

How to use penva/142-caphe-5HdchXe 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 "penva/142-caphe-5HdchXe" \
    --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": "penva/142-caphe-5HdchXe",
		"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 "penva/142-caphe-5HdchXe" \
        --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": "penva/142-caphe-5HdchXe",
		"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 penva/142-caphe-5HdchXe with Docker Model Runner:
```
docker model run hf.co/penva/142-caphe-5HdchXe
```

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.

trained_models

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Breadcrumbs with TIES merge method using vera6/affine-5GmvsbydEDvdhHy6w8JHMCorYyJPiAnvzHWaa8Aj6iTdzzns as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: breadcrumbs_ties
base_model: vera6/affine-5GmvsbydEDvdhHy6w8JHMCorYyJPiAnvzHWaa8Aj6iTdzzns
models:
  - model: DuWenJing/affine-model-5CrVf11voFhxLs2nM7LBVUKPfD4gNwYugag4Dmwe8JM423RC
    parameters:
      density: 0.95
      weight: 0.7  # Increased weight for better performance
  - model: OronoCris/affine-83-5ETkv1LSG1sMVBma1oPQUUKPkzmLDHQN7zwf8sWqCQEps3yR
    parameters:
      density: 0.8
      weight: 0.3  # Decreased weight for lower performance
parameters:
  density: 0.92
  gamma: 0.02
dtype: bfloat16

Downloads last month: -

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for penva/142-caphe-5HdchXe

DuWenJing/affine-model-5CrVf11voFhxLs2nM7LBVUKPfD4gNwYugag4Dmwe8JM423RC

OronoCris/affine-83-5ETkv1LSG1sMVBma1oPQUUKPkzmLDHQN7zwf8sWqCQEps3yR

vera6/affine-5GmvsbydEDvdhHy6w8JHMCorYyJPiAnvzHWaa8Aj6iTdzzns

Merge model

this model

Paper for penva/142-caphe-5HdchXe

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

Paper • 2312.06795 • Published Dec 11, 2023 • 2