Text Generation
Transformers
English
transwave_meyer
causal-lm
byte-level
raw-byte
attention-free
meyer
wavelet
custom_code
Instructions to use Angshul/TransWave with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Angshul/TransWave with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Angshul/TransWave", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Angshul/TransWave", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Angshul/TransWave with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Angshul/TransWave" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Angshul/TransWave", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Angshul/TransWave
- SGLang
How to use Angshul/TransWave 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 "Angshul/TransWave" \ --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": "Angshul/TransWave", "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 "Angshul/TransWave" \ --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": "Angshul/TransWave", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Angshul/TransWave with Docker Model Runner:
docker model run hf.co/Angshul/TransWave
Download config.json from Angshul/TransWave: direct link, hf CLI and curl.
- Browser
- Download file 1.06 kB
-
https://huggingface.co/Angshul/TransWave/resolve/main/config.json
- Command line
-
hf download hf://Angshul/TransWave/config.json
-
curl -L -o config.json https://huggingface.co/Angshul/TransWave/resolve/main/config.json
1.06 kB
| { | |
| "model_type": "transwave_meyer", | |
| "architectures": ["TransWaveForCausalLM"], | |
| "auto_map": { | |
| "AutoConfig": "configuration_transwave.TransWaveConfig", | |
| "AutoModelForCausalLM": "modeling_transwave.TransWaveForCausalLM" | |
| }, | |
| "vocab_size": 256, | |
| "byte_dim": 96, | |
| "bytes_per_block": 8, | |
| "num_scales": 8, | |
| "hidden_size": 768, | |
| "max_position_embeddings": 32768, | |
| "block_context": 4096, | |
| "num_hidden_layers": 12, | |
| "num_groups": 12, | |
| "meyer_bands": 12, | |
| "meyer_controls_per_band": 8, | |
| "meyer_kernel_blocks": 512, | |
| "local_kernel_blocks": 7, | |
| "intermediate_size": 2816, | |
| "decoder_hidden_size": 256, | |
| "trained_context_length": 20480, | |
| "architecture_id": "causal_transwave_blocklifting_meyer_byte_lm_g4_v2", | |
| "training_dataset": "allenai/c4:en", | |
| "training_tokens": 4499988480, | |
| "training_steps": 785, | |
| "training_physical_batch": 280, | |
| "validation_nll": 2.228725892720205, | |
| "validation_ppl": 9.288024597671594, | |
| "source_commit": "5cae31b81e15160379ded79f32bcbb443d7db9f7", | |
| "tie_word_embeddings": true | |
| } |