Instructions to use pruna-test/tiny_janus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pruna-test/tiny_janus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="pruna-test/tiny_janus")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("pruna-test/tiny_janus") model = AutoModelForMultimodalLM.from_pretrained("pruna-test/tiny_janus", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use pruna-test/tiny_janus with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pruna-test/tiny_janus" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pruna-test/tiny_janus", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/pruna-test/tiny_janus
- SGLang
How to use pruna-test/tiny_janus 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 "pruna-test/tiny_janus" \ --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": "pruna-test/tiny_janus", "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 "pruna-test/tiny_janus" \ --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": "pruna-test/tiny_janus", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use pruna-test/tiny_janus with Docker Model Runner:
docker model run hf.co/pruna-test/tiny_janus
File size: 1,999 Bytes
bf1f2d4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 | {
"architectures": [
"JanusForConditionalGeneration"
],
"dtype": "bfloat16",
"image_token_id": 100581,
"initializer_range": 0.02,
"model_type": "janus",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100000,
"dtype": "bfloat16",
"eos_token_id": 100001,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 16384,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 1,
"num_key_value_heads": 16,
"pad_token_id": 100002,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"use_cache": true,
"vocab_size": 102400
},
"transformers_version": "4.56.0",
"vision_config": {
"attention_bias": true,
"attention_dropout": 0.0,
"depth": 2,
"dtype": "bfloat16",
"hidden_act": "gelu",
"hidden_dropout_rate": 0.0,
"hidden_size": 1024,
"image_size": 384,
"initializer_range": 0.02,
"layer_norm_eps": 1e-06,
"mlp_ratio": 4.0,
"model_type": "janus_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 1,
"num_image_tokens": 576,
"patch_size": 16,
"projection_dim": 2048,
"projection_dropout": 0.0,
"use_qk_norm": false
},
"vq_config": {
"base_channels": 128,
"channel_multiplier": [
1,
1,
2,
2,
4
],
"depth": 2,
"double_latent": false,
"dropout": 0.0,
"dtype": "bfloat16",
"embed_dim": 8,
"hidden_act": "gelu",
"image_token_embed_dim": 2048,
"in_channels": 3,
"initializer_range": 0.02,
"latent_channels": 256,
"model_type": "janus_vqgan",
"num_embeddings": 16384,
"num_hidden_layers": 2,
"num_patches": 24,
"num_res_blocks": 2,
"out_channels": 3,
"projection_dim": 2048
}
}
|