Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -89,3 +89,37 @@ See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-coder/blob/main/
|
|
| 89 |
|
| 90 |
If you have any questions, please raise an issue or contact us at [agi_code@deepseek.com](mailto:agi_code@deepseek.com).
|
| 91 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 89 |
|
| 90 |
If you have any questions, please raise an issue or contact us at [agi_code@deepseek.com](mailto:agi_code@deepseek.com).
|
| 91 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
---
|
| 95 |
+
|
| 96 |
+
## Important Disclaimer
|
| 97 |
+
|
| 98 |
+
**This model has been modified to remove safety guardrails and refusal behaviors.**
|
| 99 |
+
|
| 100 |
+
### Intended Use
|
| 101 |
+
- Research and educational purposes
|
| 102 |
+
- Understanding model behavior and limitations
|
| 103 |
+
- Creative writing and roleplay with consenting adults
|
| 104 |
+
- Red-teaming and safety research
|
| 105 |
+
|
| 106 |
+
### Not Intended For
|
| 107 |
+
- Generating harmful, illegal, or unethical content
|
| 108 |
+
- Harassment, abuse, or malicious activities
|
| 109 |
+
- Misinformation or deception
|
| 110 |
+
- Any use that violates applicable laws
|
| 111 |
+
|
| 112 |
+
### User Responsibility
|
| 113 |
+
By using this model, you acknowledge that:
|
| 114 |
+
1. **You are solely responsible** for how you use this model and any content it generates
|
| 115 |
+
2. The model creator **accepts no liability** for misuse or harmful outputs
|
| 116 |
+
3. You will comply with all applicable laws and ethical guidelines
|
| 117 |
+
4. You understand this model may produce inaccurate, biased, or inappropriate content
|
| 118 |
+
|
| 119 |
+
### Technical Note
|
| 120 |
+
This model was created using abliteration techniques that suppress the "refusal direction" in the model's activation space. This does not add new capabilities—it only removes trained refusal behaviors from the base model.
|
| 121 |
+
|
| 122 |
+
**Use responsibly. You have been warned.**
|
| 123 |
+
|
| 124 |
+
---
|
| 125 |
+
|