Instructions to use amete7/qvla with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amete7/qvla with Transformers:

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

pipe = pipeline("image-text-to-text", model="amete7/qvla", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("amete7/qvla", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use amete7/qvla with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amete7/qvla"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amete7/qvla",
		"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/amete7/qvla

SGLang

How to use amete7/qvla 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 "amete7/qvla" \
    --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": "amete7/qvla",
		"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 "amete7/qvla" \
        --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": "amete7/qvla",
		"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 amete7/qvla with Docker Model Runner:
```
docker model run hf.co/amete7/qvla
```

qvla / config.json

Atharva Mete

vla added but giving nans in loss

57b4d23 over 1 year ago

raw

history blame contribute delete

866 Bytes

	{
	"architectures": [
	"MolmoForCausalLM"
	],
	"attention_layer_norm": false,
	"auto_map": {
	"AutoConfig": "config_molmo.MolmoConfig",
	"AutoModelForCausalLM": "modeling_molmo.MolmoForCausalLM"
	},
	"clip_qkv": null,
	"embedding_size": 152064,
	"hidden_size": 3584,
	"initializer_range": 0.02,
	"intermediate_size": 37888,
	"layer_norm_eps": 1e-06,
	"layer_norm_type": "rms",
	"max_position_embeddings": 4096,
	"model_type": "molmo",
	"norm_after": false,
	"num_attention_heads": 28,
	"num_hidden_layers": 28,
	"num_key_value_heads": 4,
	"qkv_bias": true,
	"rope_theta": 1000000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.43.3",
	"use_cache": true,
	"use_position_ids": true,
	"vocab_size": 152064,
	"skill_vocab_size": 1000,
	"additional_vocab_size": 128,
	"weight_tying": false
	}