Upload model via Google Colab

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-llama-8b-enkrypt-aligned-F16.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-llama-8b-enkrypt-aligned-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-llama-8b-enkrypt-aligned-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-llama-8b-enkrypt-aligned-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-llama-8b-enkrypt-aligned-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-llama-8b-enkrypt-aligned-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-distill-llama-8b-enkrypt-aligned-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix.dat filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,83 @@
+---
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+---
+# DeepSeek-R1-Distill-Llama-8B-ENK-Aligned
+
+## Overview
+
+**DeepSeek-R1-Distill-Llama-8B-ENK-Aligned** is a safety-aligned version of [`deepseek-ai/DeepSeek-R1-Distill-Llama-8B`](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B). It has been aligned using the **Enkrypt AI Safety Alignment dataset**, which was generated with the **SAGE** process:
+
+> **SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming**  
+> Anurakt Kumar, Divyanshu Kumar, Jatan Loya, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi (2024)  
+> [[arXiv:2408.11851]](https://arxiv.org/abs/2408.11851)
+
+This alignment significantly **reduces toxicity, harmfulness, and jailbreak vulnerabilities** across various safety topics while **maintaining model performance**.
+
+## Red Team Results
+
+![Safety Comparison](assets/safety_comparison.png)
+
+## Performance Results
+| Model | MMLU-Pro Score |
+|--------|----------------|
+| DeepSeek-R1-Distill-Llama-8B (Base) | **44.71** |
+| DeepSeek-R1-Distill-Llama-8B-ENK-Aligned | **46.43** |
+
+## Training Configuration
+
+The model was trained using the **SimPO (Simple Preference Optimization)** approach with the following hyperparameters:
+
+```yaml
+cpo_config:
+  loss_type: 'simpo'
+  max_prompt_length: 1800
+  max_length: 3600
+  per_device_train_batch_size: 8
+  gradient_accumulation_steps: 1
+  learning_rate: 1.8e-6
+  optim: 'adamw_torch'
+  lr_scheduler_type: 'cosine'
+  gradient_checkpointing: True
+  beta: 5
+  num_train_epochs: 1
+  bf16: False
+  simpo_gamma: 0.8
+  warmup_ratio: 0.1
+  cpo_alpha: 0.0
+```
+
+## Key Improvements
+
+- **Enhanced Safety**: Significant reduction in harmful or toxic outputs.
+- **Improved Robustness**: Stronger resistance to adversarial jailbreak prompts.
+- **Minimal Performance Tradeoff**: Slight improvement in MMLU-Pro despite additional alignment constraints.
+
+## Use Cases
+
+This model is ideal for applications requiring **safe, aligned, and high-performance language generation**, including:
+- **Conversational AI**: Ensuring responsible and aligned assistant behavior.
+- **Content Moderation**: Filtering harmful content while maintaining contextual understanding.
+- **Education & Research**: Deploying AI in sensitive environments with reduced risks.
+
+<!-- ## Citation
+
+If you use this model, please cite the SAGE-RT paper:
+
+```bibtex
+@misc{kumar2024sagertsyntheticalignmentdata,
+  title={SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming},
+  author={Anurakt Kumar and Divyanshu Kumar and Jatan Loya and Nitin Aravind Birur and Tanay Baswa and Sahil Agarwal and Prashanth Harshangi},
+  year={2024},
+  eprint={2408.11851},
+  archivePrefix={arXiv},
+  primaryClass={cs.AI},
+  url={https://arxiv.org/abs/2408.11851}
+}
+``` -->
+
+---
+For questions or contributions, reach out to the **Enkrypt AI** team!
+
+
+

deepseek-r1-distill-llama-8b-enkrypt-aligned-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0170a9622f0e6636e899b40f5a19eb316df8879f10e744de9a347800be7c7a74
+size 16068894048

deepseek-r1-distill-llama-8b-enkrypt-aligned-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc613a2bb9fed4b12e4a438a237cda52ab8b031ce2ed81a0f4099b4874914a7d
+size 3179134304

deepseek-r1-distill-llama-8b-enkrypt-aligned-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53cb8a4f08bf1b8e900b195eacb935588cbe178f2865efd9e2fec432e76c17b7
+size 4018920800

deepseek-r1-distill-llama-8b-enkrypt-aligned-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f8464bb143fdcee9fd273fc46f194cfab7f487346268037a68449eaf58c9bf
+size 4920737120

deepseek-r1-distill-llama-8b-enkrypt-aligned-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e7b2dbedc718b3eace6847ecea2cd3a8c7ead2ca7976279832befc7f771a29
+size 5732990304

deepseek-r1-distill-llama-8b-enkrypt-aligned-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59048148d770bc102860c9463095059a793c9fd886f1a6adde45d109b827e54e
+size 6596009312

deepseek-r1-distill-llama-8b-enkrypt-aligned-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfc35570f680d01d6dbf6971ec2726469807be6a781984e1abb64db34929f6f
+size 8540773728

imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632578c0108e00ced9ecff71f92dde536913679e1da7b4b9ce99d3a3fa681881
+size 4988189