Instructions to use rbln/tiny-Llama4ForConditionalGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rbln/tiny-Llama4ForConditionalGeneration with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="rbln/tiny-Llama4ForConditionalGeneration")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("rbln/tiny-Llama4ForConditionalGeneration") model = AutoModelForMultimodalLM.from_pretrained("rbln/tiny-Llama4ForConditionalGeneration", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use rbln/tiny-Llama4ForConditionalGeneration with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rbln/tiny-Llama4ForConditionalGeneration" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rbln/tiny-Llama4ForConditionalGeneration", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rbln/tiny-Llama4ForConditionalGeneration
- SGLang
How to use rbln/tiny-Llama4ForConditionalGeneration 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 "rbln/tiny-Llama4ForConditionalGeneration" \ --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": "rbln/tiny-Llama4ForConditionalGeneration", "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 "rbln/tiny-Llama4ForConditionalGeneration" \ --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": "rbln/tiny-Llama4ForConditionalGeneration", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rbln/tiny-Llama4ForConditionalGeneration with Docker Model Runner:
docker model run hf.co/rbln/tiny-Llama4ForConditionalGeneration
Download config.json from rbln/tiny-Llama4ForConditionalGeneration: direct link, hf CLI and curl.
- Browser
- Download file 2.64 kB
-
https://huggingface.co/rbln/tiny-Llama4ForConditionalGeneration/resolve/main/config.json
- Command line
-
hf download hf://rbln/tiny-Llama4ForConditionalGeneration/config.json
-
curl -L -o config.json https://huggingface.co/rbln/tiny-Llama4ForConditionalGeneration/resolve/main/config.json
2.64 kB
| { | |
| "architectures": [ | |
| "Llama4ForConditionalGeneration" | |
| ], | |
| "boi_token_index": 200080, | |
| "dtype": "float32", | |
| "eoi_token_index": 200081, | |
| "image_token_index": 200092, | |
| "model_type": "llama4", | |
| "text_config": { | |
| "_attn_implementation_autoset": true, | |
| "attention_bias": false, | |
| "attention_chunk_size": 128, | |
| "attention_dropout": 0.0, | |
| "attn_scale": 0.1, | |
| "attn_temperature_tuning": true, | |
| "bos_token_id": 200000, | |
| "cache_implementation": "static", | |
| "dtype": "float32", | |
| "eos_token_id": [ | |
| 200001, | |
| 200007, | |
| 200008 | |
| ], | |
| "floor_scale": 8192, | |
| "for_llm_compressor": false, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 8, | |
| "initializer_range": 0.02, | |
| "interleave_moe_layer_step": 0, | |
| "intermediate_size": 32, | |
| "intermediate_size_mlp": 32, | |
| "layer_types": [ | |
| "chunked_attention", | |
| "chunked_attention", | |
| "chunked_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 1024, | |
| "model_type": "llama4_text", | |
| "moe_layers": [], | |
| "no_rope_layer_interval": 4, | |
| "no_rope_layers": [ | |
| 1, | |
| 1, | |
| 1, | |
| 0 | |
| ], | |
| "num_attention_heads": 4, | |
| "num_experts_per_tok": 1, | |
| "num_hidden_layers": 4, | |
| "num_key_value_heads": 2, | |
| "num_local_experts": 0, | |
| "output_router_logits": false, | |
| "pad_token_id": 200018, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "factor": 16, | |
| "high_freq_factor": 1, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_theta": 500000.0, | |
| "rope_type": "llama3" | |
| }, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "tie_word_embeddings": false, | |
| "use_cache": true, | |
| "use_qk_norm": true, | |
| "vocab_size": 202048 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.15.1", | |
| "vision_config": { | |
| "_attn_implementation_autoset": true, | |
| "attention_dropout": 0.0, | |
| "dtype": "float32", | |
| "hidden_act": "gelu", | |
| "hidden_size": 16, | |
| "image_size": 336, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 64, | |
| "model_type": "llama4_vision_model", | |
| "multi_modal_projector_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 4, | |
| "num_channels": 3, | |
| "num_hidden_layers": 2, | |
| "patch_size": 14, | |
| "pixel_shuffle_ratio": 0.5, | |
| "projector_dropout": 0.0, | |
| "projector_input_dim": 16, | |
| "projector_output_dim": 16, | |
| "rope_parameters": { | |
| "rope_theta": 10000, | |
| "rope_type": "default" | |
| }, | |
| "vision_feature_layer": -1, | |
| "vision_feature_select_strategy": "default", | |
| "vision_output_dim": 16 | |
| } | |
| } | |