Instructions to use Delower/Llama4Text with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Delower/Llama4Text with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Delower/Llama4Text")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Delower/Llama4Text") model = AutoModelForCausalLM.from_pretrained("Delower/Llama4Text", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Delower/Llama4Text with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Delower/Llama4Text" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Delower/Llama4Text", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Delower/Llama4Text
- SGLang
How to use Delower/Llama4Text 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 "Delower/Llama4Text" \ --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": "Delower/Llama4Text", "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 "Delower/Llama4Text" \ --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": "Delower/Llama4Text", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Delower/Llama4Text with Docker Model Runner:
docker model run hf.co/Delower/Llama4Text
Download config.json from Delower/Llama4Text: direct link, hf CLI and curl.
- Browser
- Download file 1.17 kB
-
https://huggingface.co/Delower/Llama4Text/resolve/main/config.json
- Command line
-
hf download hf://Delower/Llama4Text/config.json
-
curl -L -o config.json https://huggingface.co/Delower/Llama4Text/resolve/main/config.json
1.17 kB
| { | |
| "architectures": [ | |
| "Llama4ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_chunk_size": 8192, | |
| "attention_dropout": 0.0, | |
| "attn_scale": 0.1, | |
| "attn_temperature_tuning": true, | |
| "bos_token_id": 1, | |
| "cache_implementation": "hybrid", | |
| "eos_token_id": 2, | |
| "floor_scale": 8192, | |
| "head_dim": 32, | |
| "hidden_act": "silu", | |
| "hidden_size": 384, | |
| "initializer_range": 0.02, | |
| "interleave_moe_layer_step": 1, | |
| "intermediate_size": 1024, | |
| "intermediate_size_mlp": 256, | |
| "max_position_embeddings": 512, | |
| "model_type": "llama4_text", | |
| "moe_layers": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5 | |
| ], | |
| "no_rope_layers": [ | |
| 1, | |
| 1, | |
| 1, | |
| 0, | |
| 1, | |
| 1 | |
| ], | |
| "num_attention_heads": 4, | |
| "num_experts_per_tok": 1, | |
| "num_hidden_layers": 6, | |
| "num_key_value_heads": 4, | |
| "num_local_experts": 16, | |
| "output_router_logits": false, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "use_qk_norm": true, | |
| "vocab_size": 58 | |
| } | |