Instructions to use Lanni-ni/test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lanni-ni/test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Lanni-ni/test", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Lanni-ni/test", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Lanni-ni/test with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Lanni-ni/test" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lanni-ni/test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Lanni-ni/test
- SGLang
How to use Lanni-ni/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 "Lanni-ni/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": "Lanni-ni/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 "Lanni-ni/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": "Lanni-ni/test", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Lanni-ni/test with Docker Model Runner:
docker model run hf.co/Lanni-ni/test
| { | |
| "architectures": [ | |
| "DynamicSlidingWindowForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "auto_map": { | |
| "AutoConfig": "configuration_dynamic_sliding_window.DynamicSlidingWindowConfig", | |
| "AutoModelForCausalLM": "modeling_dynamic_sliding_window.DynamicSlidingWindowForCausalLM" | |
| }, | |
| "bos_token_id": null, | |
| "context_length": 512, | |
| "elementwise_affine": true, | |
| "eos_token_id": null, | |
| "fuse_cross_entropy": true, | |
| "fuse_norm": true, | |
| "hidden_act": "swish", | |
| "hidden_ratio": 4, | |
| "hidden_size": 256, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1024, | |
| "max_position_embeddings": null, | |
| "model_type": "dynamic_sliding_window", | |
| "norm_eps": 1e-06, | |
| "num_heads": 4, | |
| "num_hidden_layers": 2, | |
| "num_kv_heads": null, | |
| "qk_norm": false, | |
| "qk_norm_share_param_across_head": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.0", | |
| "use_cache": true, | |
| "use_dynamic_window": true, | |
| "use_k_shift": false, | |
| "use_rope": false, | |
| "use_v_shift": false, | |
| "vocab_size": 50277, | |
| "window_decay_rate": 0.6, | |
| "window_initial_lambda": 1.0, | |
| "window_num_epochs": 10 | |
| } | |