Text Generation
Transformers
PyTorch
English
experimental
research
bit-level
transformer
reversible
safety
telemetry
language-modeling
Instructions to use WCNegentropy/BitTransformerLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use WCNegentropy/BitTransformerLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="WCNegentropy/BitTransformerLM")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WCNegentropy/BitTransformerLM", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use WCNegentropy/BitTransformerLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "WCNegentropy/BitTransformerLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "WCNegentropy/BitTransformerLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/WCNegentropy/BitTransformerLM
- SGLang
How to use WCNegentropy/BitTransformerLM 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 "WCNegentropy/BitTransformerLM" \ --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": "WCNegentropy/BitTransformerLM", "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 "WCNegentropy/BitTransformerLM" \ --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": "WCNegentropy/BitTransformerLM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use WCNegentropy/BitTransformerLM with Docker Model Runner:
docker model run hf.co/WCNegentropy/BitTransformerLM
| from .model import ( | |
| PositionalEncoding, | |
| BitTransformerLM, | |
| ReversibleLoggingTransformerEncoderLayer, | |
| example_usage, | |
| example_training_step, | |
| infer_long_sequence, | |
| diffusion_inference, | |
| ) | |
| from .telemetry import TelemetrySynthesizer, detect_metric_drift | |
| from .dashboard import plot_telemetry | |
| from .dashboard_app import run_dashboard | |
| from .collapse import collapse_submodel, save_distilled_model | |
| from .safety import hil_safe_inference, demo_hil_safety, safe_sample_with_retry | |
| from .bit_io import ( | |
| text_to_bits, | |
| bits_to_text, | |
| infer_text, | |
| ) | |
| from .parity import enforce_parity | |
| from .compression import ( | |
| compress_bits, | |
| decompress_bits, | |
| model_output_decompress, | |
| pack_bits, | |
| unpack_bits, | |
| ) | |
| from .distributed import wrap_fsdp, make_pipeline | |
| from .optimization import configure_optimizer, adjust_learning_rate | |
| from .scale import expand_model | |
| from .distil import distill_step, TelemetryLog | |
| from .quantization import ( | |
| quantize_dynamic, | |
| prepare_qat_fx, | |
| convert_qat_fx, | |
| ) | |
| from .training import train_loop | |
| from .utils import save_model, load_model, set_dropout | |
| from .hf_checkpoint import hf_login, save_checkpoint, download_checkpoint | |
| from .torch_utils import cpu_autocast | |
| __all__ = [ | |
| "PositionalEncoding", | |
| "BitTransformerLM", | |
| "ReversibleLoggingTransformerEncoderLayer", | |
| "example_usage", | |
| "example_training_step", | |
| "TelemetrySynthesizer", | |
| "detect_metric_drift", | |
| "collapse_submodel", | |
| "save_distilled_model", | |
| "hil_safe_inference", | |
| "demo_hil_safety", | |
| "safe_sample_with_retry", | |
| "text_to_bits", | |
| "bits_to_text", | |
| "infer_text", | |
| "enforce_parity", | |
| "plot_telemetry", | |
| "run_dashboard", | |
| "configure_optimizer", | |
| "adjust_learning_rate", | |
| "expand_model", | |
| "distill_step", | |
| "TelemetryLog", | |
| "quantize_dynamic", | |
| "prepare_qat_fx", | |
| "convert_qat_fx", | |
| "train_loop", | |
| "wrap_fsdp", | |
| "make_pipeline", | |
| "compress_bits", | |
| "decompress_bits", | |
| "model_output_decompress", | |
| "pack_bits", | |
| "unpack_bits", | |
| "infer_long_sequence", | |
| "diffusion_inference", | |
| "save_model", | |
| "load_model", | |
| "set_dropout", | |
| "hf_login", | |
| "save_checkpoint", | |
| "download_checkpoint", | |
| "cpu_autocast", | |
| ] | |