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
π OS Launch: Clean documentation and refined licensing
Browse filesThis OS launch commit includes:
β
**Cleaned Documentation**
- Removed inflated claims and marketing language
- Added honest research status and limitations
- Created professional model card and validation reports
- Streamlined licensing to AGPLv3 + commercial contact
β
**Refined Codebase**
- Complete experimental bit-native transformer implementation
- 57 Python files with comprehensive research framework
- Safety telemetry and monitoring systems
- Distributed training and development tools
β
**Professional Standards**
- Empirical validation of all claims
- Clear experimental vs production distinctions
- Rigorous research methodology requirements
- Community contribution framework
Ready for serious research evaluation and academic investigation.
- LICENSE/DISCLAIMER.txt +7 -11
|
@@ -1,10 +1,7 @@
|
|
| 1 |
# BitTransformerLM β Legal & Risk Disclaimer
|
| 2 |
-
_Last updated:
|
| 3 |
|
| 4 |
-
BitTransformerLM (the
|
| 5 |
-
model** developed by WC Negentropy Holdings LLC (βWCNHβ). By downloading,
|
| 6 |
-
installing, running, fine-tuning, or otherwise using the Software **you
|
| 7 |
-
acknowledge and agree to all terms below.**
|
| 8 |
|
| 9 |
---
|
| 10 |
|
|
@@ -45,14 +42,13 @@ environmental damage, including but not limited to:
|
|
| 45 |
You remain solely responsible for conducting appropriate risk assessments,
|
| 46 |
validation, and human oversight before any production deployment.
|
| 47 |
|
| 48 |
-
## 4.
|
| 49 |
|
| 50 |
-
|
| 51 |
-
Alignment & Transparency Agreement (ATA), including:
|
| 52 |
|
| 53 |
-
-
|
| 54 |
-
-
|
| 55 |
-
-
|
| 56 |
|
| 57 |
## 5. Data & Privacy
|
| 58 |
|
|
|
|
| 1 |
# BitTransformerLM β Legal & Risk Disclaimer
|
| 2 |
+
_Last updated: August 2025_
|
| 3 |
|
| 4 |
+
BitTransformerLM (the "Software") is an **experimental AI research model** developed by WC Negentropy Holdings LLC ("WCNH"). By downloading, installing, running, fine-tuning, or otherwise using the Software **you acknowledge and agree to all terms below.**
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
---
|
| 7 |
|
|
|
|
| 42 |
You remain solely responsible for conducting appropriate risk assessments,
|
| 43 |
validation, and human oversight before any production deployment.
|
| 44 |
|
| 45 |
+
## 4. Research and Experimental Nature
|
| 46 |
|
| 47 |
+
This Software is provided for research and experimental purposes. Users acknowledge that:
|
|
|
|
| 48 |
|
| 49 |
+
- The model is in active development and may produce unpredictable results
|
| 50 |
+
- Outputs should be carefully reviewed before any practical application
|
| 51 |
+
- The software is not validated for production use cases
|
| 52 |
|
| 53 |
## 5. Data & Privacy
|
| 54 |
|