Instructions to use SimoneLuchini111/PixtralMultitask_PilotV4_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SimoneLuchini111/PixtralMultitask_PilotV4_test with Transformers:

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

pipe = pipeline("image-text-to-text", model="SimoneLuchini111/PixtralMultitask_PilotV4_test")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("SimoneLuchini111/PixtralMultitask_PilotV4_test")
model = AutoModelForMultimodalLM.from_pretrained("SimoneLuchini111/PixtralMultitask_PilotV4_test", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SimoneLuchini111/PixtralMultitask_PilotV4_test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SimoneLuchini111/PixtralMultitask_PilotV4_test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SimoneLuchini111/PixtralMultitask_PilotV4_test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SimoneLuchini111/PixtralMultitask_PilotV4_test

SGLang

How to use SimoneLuchini111/PixtralMultitask_PilotV4_test 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 "SimoneLuchini111/PixtralMultitask_PilotV4_test" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SimoneLuchini111/PixtralMultitask_PilotV4_test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "SimoneLuchini111/PixtralMultitask_PilotV4_test" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SimoneLuchini111/PixtralMultitask_PilotV4_test",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SimoneLuchini111/PixtralMultitask_PilotV4_test with Docker Model Runner:
```
docker model run hf.co/SimoneLuchini111/PixtralMultitask_PilotV4_test
```

PixtralMultitask_PilotV4_test / config.json

SimoneLuchini111

Upload LlavaForConditionalGeneration

73ab6a6 verified over 1 year ago

Raw

History Blame Contribute Delete

1.41 kB

	{
	"architectures": [
	"LlavaForConditionalGeneration"
	],
	"ignore_index": -100,
	"image_seq_length": 1,
	"image_token_index": 10,
	"model_type": "llava",
	"multimodal_projector_bias": true,
	"projector_hidden_act": "gelu",
	"text_config": {
	"attention_dropout": 0.0,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 5120,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"is_composition": true,
	"max_position_embeddings": 1024000,
	"model_type": "mistral",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 8,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 1000000000.0,
	"sliding_window": null,
	"torch_dtype": "bfloat16",
	"use_cache": true,
	"vocab_size": 131072
	},
	"torch_dtype": "bfloat16",
	"transformers_version": "4.51.2",
	"vision_config": {
	"attention_dropout": 0.0,
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 1024,
	"image_size": 1024,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"is_composition": true,
	"model_type": "pixtral",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"patch_size": 16,
	"rope_theta": 10000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16"
	},
	"vision_feature_layer": -1,
	"vision_feature_select_strategy": "full"
	}