Instructions to use teilers/mamba-constrict-td with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use teilers/mamba-constrict-td with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="teilers/mamba-constrict-td")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("teilers/mamba-constrict-td") model = AutoModel.from_pretrained("teilers/mamba-constrict-td") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use teilers/mamba-constrict-td with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "teilers/mamba-constrict-td" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "teilers/mamba-constrict-td", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/teilers/mamba-constrict-td
- SGLang
How to use teilers/mamba-constrict-td 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 "teilers/mamba-constrict-td" \ --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": "teilers/mamba-constrict-td", "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 "teilers/mamba-constrict-td" \ --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": "teilers/mamba-constrict-td", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use teilers/mamba-constrict-td with Docker Model Runner:
docker model run hf.co/teilers/mamba-constrict-td
| { | |
| "architectures": [ | |
| "MambaModel" | |
| ], | |
| "bos_token_id": 0, | |
| "conv_kernel": 4, | |
| "dtype": "float32", | |
| "eos_token_id": 0, | |
| "expand": 2, | |
| "fused_add_norm": true, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.1, | |
| "intermediate_size": 5120, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "mamba", | |
| "n_layer": 64, | |
| "num_hidden_layers": 64, | |
| "pad_token_id": 0, | |
| "pad_vocab_size_multiple": 8, | |
| "rescale_prenorm_residual": false, | |
| "residual_in_fp32": true, | |
| "rms_norm": true, | |
| "state_size": 16, | |
| "time_step_floor": 0.0001, | |
| "time_step_init_scheme": "random", | |
| "time_step_max": 0.1, | |
| "time_step_min": 0.001, | |
| "time_step_rank": 160, | |
| "time_step_scale": 1.0, | |
| "transformers_version": "4.57.3", | |
| "use_bias": false, | |
| "use_cache": true, | |
| "use_conv_bias": true, | |
| "use_mambapy": false, | |
| "vocab_size": 50280 | |
| } | |