Text Generation
Transformers
cenn
knowledge-distillation
transformer-free
language-modeling
recurrent-neural-network
Instructions to use vtava/TinyCeNN-LM-Distilled with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vtava/TinyCeNN-LM-Distilled with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="vtava/TinyCeNN-LM-Distilled")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vtava/TinyCeNN-LM-Distilled", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use vtava/TinyCeNN-LM-Distilled with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "vtava/TinyCeNN-LM-Distilled" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "vtava/TinyCeNN-LM-Distilled", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/vtava/TinyCeNN-LM-Distilled
- SGLang
How to use vtava/TinyCeNN-LM-Distilled 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 "vtava/TinyCeNN-LM-Distilled" \ --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": "vtava/TinyCeNN-LM-Distilled", "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 "vtava/TinyCeNN-LM-Distilled" \ --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": "vtava/TinyCeNN-LM-Distilled", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use vtava/TinyCeNN-LM-Distilled with Docker Model Runner:
docker model run hf.co/vtava/TinyCeNN-LM-Distilled
Download student_config.json from vtava/TinyCeNN-LM-Distilled: direct link, hf CLI and curl.
- Browser
- Download file 437 Bytes
-
https://huggingface.co/vtava/TinyCeNN-LM-Distilled/resolve/main/student_config.json
- Command line
-
hf download hf://vtava/TinyCeNN-LM-Distilled/student_config.json
-
curl -L -o student_config.json https://huggingface.co/vtava/TinyCeNN-LM-Distilled/resolve/main/student_config.json
437 Bytes
| { | |
| "format_version": 1, | |
| "architecture": "cenn-only-replacement", | |
| "base_model": "arnir0/Tiny-LLM", | |
| "layer_indices": [ | |
| 0 | |
| ], | |
| "cenn": { | |
| "hidden_size": 192, | |
| "kernel_size": 3, | |
| "expansion": 4, | |
| "steps": 7, | |
| "dilations": [ | |
| 1, | |
| 2, | |
| 4, | |
| 8, | |
| 16, | |
| 32, | |
| 64 | |
| ], | |
| "rms_norm_eps": 1e-05, | |
| "dropout": 0.0 | |
| }, | |
| "training": { | |
| "distilled": true, | |
| "tokens": 9420800 | |
| } | |
| } |