Text Generation
Transformers
Safetensors
taonet
trust-remote-code
sentencepiece
custom-architecture
custom_code
Instructions to use TaoTern/TaoNet-mini-A2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TaoTern/TaoNet-mini-A2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TaoTern/TaoNet-mini-A2", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("TaoTern/TaoNet-mini-A2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TaoTern/TaoNet-mini-A2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TaoTern/TaoNet-mini-A2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TaoTern/TaoNet-mini-A2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TaoTern/TaoNet-mini-A2
- SGLang
How to use TaoTern/TaoNet-mini-A2 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 "TaoTern/TaoNet-mini-A2" \ --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": "TaoTern/TaoNet-mini-A2", "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 "TaoTern/TaoNet-mini-A2" \ --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": "TaoTern/TaoNet-mini-A2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TaoTern/TaoNet-mini-A2 with Docker Model Runner:
docker model run hf.co/TaoTern/TaoNet-mini-A2
| { | |
| "architectures": [ | |
| "TaoNetForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_taonet.TaoNetConfig", | |
| "AutoModelForCausalLM": "modeling_taonet.TaoNetForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "cnn_channels": [ | |
| 32, | |
| 64, | |
| 128 | |
| ], | |
| "cnn_kernel_size": 3, | |
| "d_embed_rank": 96, | |
| "d_latent_kv": 768, | |
| "d_rope": 128, | |
| "dropout": 0.02, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "gamma_activation": "gelu", | |
| "gamma_discretization": "bilinear", | |
| "gamma_dt_init": 0.01, | |
| "gamma_dt_max": 0.1, | |
| "gamma_dt_min": 0.001, | |
| "gamma_gate": true, | |
| "gamma_gate_bias": 2.0, | |
| "gamma_hidden_dim": 1536, | |
| "gamma_input_gate": true, | |
| "gamma_input_gate_bias": 2.0, | |
| "gamma_kernel_mode": "auto", | |
| "gamma_kernel_threshold": 64, | |
| "gamma_layer_scale_init": 0.1, | |
| "gamma_prenorm": true, | |
| "gamma_residual_scale": 1.0, | |
| "gamma_use_D": true, | |
| "gamma_use_output_linear": true, | |
| "gqa_groups": 1, | |
| "head_dim": 128, | |
| "hidden_dim": 1024, | |
| "hidden_dim_ff": 3072, | |
| "image_size": 224, | |
| "image_token": "<image>", | |
| "init_std": 0.02, | |
| "intermediate_dim": 4096, | |
| "max_seq_length": 1024, | |
| "model_type": "taonet", | |
| "num_heads": 8, | |
| "num_layers": 16, | |
| "pad_token_id": 3, | |
| "rope_scale": 40.0, | |
| "transformers_version": "5.1.0", | |
| "unk_token_id": 0, | |
| "use_factorized_embedding": true, | |
| "vision_encoder_type": "cnn", | |
| "vision_output_dim": 256, | |
| "vision_prefix_tokens": 10, | |
| "vocab_size": 8192, | |
| "yarn_alpha": 1.0, | |
| "yarn_enabled": false, | |
| "yarn_original_max_seq_length": null | |
| } | |