tiny-random-LlavaForConditionalGeneration_phi

Instructions to use Xenova/tiny-random-LlavaForConditionalGeneration_phi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xenova/tiny-random-LlavaForConditionalGeneration_phi with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('image-text-to-text', 'Xenova/tiny-random-LlavaForConditionalGeneration_phi');

Transformers

How to use Xenova/tiny-random-LlavaForConditionalGeneration_phi with Transformers:

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

pipe = pipeline("image-text-to-text", model="Xenova/tiny-random-LlavaForConditionalGeneration_phi")

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

processor = AutoProcessor.from_pretrained("Xenova/tiny-random-LlavaForConditionalGeneration_phi")
model = AutoModelForMultimodalLM.from_pretrained("Xenova/tiny-random-LlavaForConditionalGeneration_phi", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Xenova/tiny-random-LlavaForConditionalGeneration_phi with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Xenova/tiny-random-LlavaForConditionalGeneration_phi

SGLang

How to use Xenova/tiny-random-LlavaForConditionalGeneration_phi 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 "Xenova/tiny-random-LlavaForConditionalGeneration_phi" \
    --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": "Xenova/tiny-random-LlavaForConditionalGeneration_phi",
		"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 "Xenova/tiny-random-LlavaForConditionalGeneration_phi" \
        --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": "Xenova/tiny-random-LlavaForConditionalGeneration_phi",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Xenova/tiny-random-LlavaForConditionalGeneration_phi with Docker Model Runner:
```
docker model run hf.co/Xenova/tiny-random-LlavaForConditionalGeneration_phi
```

tiny-random-LlavaForConditionalGeneration_phi

File size: 1,562 Bytes

{
  "_name_or_path": "Xenova/tiny-random-LlavaForConditionalGeneration",
  "architectures": [
    "LlavaForConditionalGeneration"
  ],
  "ignore_index": -100,
  "image_token_index": 32000,
  "model_type": "llava",
  "projector_hidden_act": "gelu",
  "text_config": {
    "architectures": [
      "PhiForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 0,
    "embd_pdrop": 0.0,
    "eos_token_id": 1,
    "hidden_act": "silu",
    "hidden_size": 16,
    "initializer_range": 0.02,
    "intermediate_size": 64,
    "layer_norm_eps": 1e-05,
    "max_position_embeddings": 2048,
    "model_type": "phi",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "num_key_value_heads": 4,
    "pad_token_id": -1,
    "partial_rotary_factor": 0.5,
    "pretraining_tp": 1,
    "qk_layernorm": false,
    "resid_pdrop": 0.0,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000.0,
    "tie_word_embeddings": false,
    "torch_dtype": "float32",
    "transformers_version": "4.38.2",
    "use_cache": true,
    "vocab_size": 32002
  },
  "torch_dtype": "float32",
  "transformers_version": "4.38.2",
  "vision_config": {
    "attention_dropout": 0.1,
    "dropout": 0.1,
    "hidden_size": 32,
    "image_size": 30,
    "intermediate_size": 37,
    "model_type": "clip_vision_model",
    "num_attention_heads": 4,
    "num_hidden_layers": 2,
    "patch_size": 2,
    "projection_dim": 32
  },
  "vision_feature_layer": -2,
  "vision_feature_select_strategy": "default",
  "vocab_size": 32002
}