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", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- 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
🚀 Refined BitTransformerLM: Organized codebase with best practices
Browse files
scripts/tools/RELEASE_INFO.md
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# BitTransformerLM v0.1.0 - Experimental Research Release
|
| 2 |
+
|
| 3 |
+
**Release Date:** August 2025
|
| 4 |
+
**Status:** Open Source Research Implementation
|
| 5 |
+
**License:** AGPLv3 + Commercial Licensing Available
|
| 6 |
+
|
| 7 |
+
## What's Included
|
| 8 |
+
|
| 9 |
+
This release provides a complete experimental framework for bit-native language modeling research:
|
| 10 |
+
|
| 11 |
+
- **Core Architecture:** 57 Python files implementing bit-native transformer with reversible layers
|
| 12 |
+
- **Safety Systems:** Real-time K/C/S telemetry and monitoring
|
| 13 |
+
- **Research Tools:** Interactive dashboard, distributed training, comprehensive testing
|
| 14 |
+
- **Documentation:** Professional model card, research status, and validation reports
|
| 15 |
+
|
| 16 |
+
## Important Notes
|
| 17 |
+
|
| 18 |
+
⚠️ **Experimental Status:** This is research code requiring rigorous baseline validation
|
| 19 |
+
⚠️ **Not Production Ready:** Needs extensive evaluation vs standard transformers
|
| 20 |
+
⚠️ **Research Use Only:** Intended for academic investigation and experimentation
|
| 21 |
+
|
| 22 |
+
## Licensing
|
| 23 |
+
|
| 24 |
+
- **Open Source:** AGPLv3 for research and open source use
|
| 25 |
+
- **Commercial:** Contact contact@wcnegentropy.com for commercial licensing
|
| 26 |
+
|
| 27 |
+
## Next Steps
|
| 28 |
+
|
| 29 |
+
The research community is invited to:
|
| 30 |
+
1. Conduct rigorous baseline comparisons vs standard transformers
|
| 31 |
+
2. Evaluate on established language modeling benchmarks
|
| 32 |
+
3. Validate (or refute) claimed memory efficiency benefits
|
| 33 |
+
4. Share findings openly to advance the field
|
| 34 |
+
|
| 35 |
+
**Research responsibly. Validate rigorously. Share openly.**
|