Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
base_model:
|
|
|
|
|
|
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
- tr
|
|
@@ -12,10 +14,41 @@ tags:
|
|
| 12 |
- ethicalhacking
|
| 13 |
- informationsecurity
|
| 14 |
- pentest
|
| 15 |
-
- llama-cpp
|
| 16 |
-
- gguf-my-repo
|
| 17 |
---
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
# AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3-Safe-Q8_0-GGUF
|
| 20 |
This model was converted to GGUF format from [`AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3-Safe`](https://huggingface.co/AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3-Safe) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 21 |
Refer to the [original model card](https://huggingface.co/AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3-Safe) for more details on the model.
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
base_model:
|
| 4 |
+
- AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3
|
| 5 |
+
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
- tr
|
|
|
|
| 14 |
- ethicalhacking
|
| 15 |
- informationsecurity
|
| 16 |
- pentest
|
|
|
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
+
<img src="https://huggingface.co/AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3-Safe/resolve/main/DALL%C2%B7E%202025-01-26%2005.35.30%20-%20A%20cute%20Fox%20Terrier%20dog%20in%20a%20cyberpunk%20style%2C%20running%20joyfully%20with%20a%20playful%20and%20friendly%20expression.%20The%20dog%20has%20wire-haired%20white%20and%20tan%20fur%20with%20g.webp" width="1000" />
|
| 20 |
+
|
| 21 |
+
Curated and trained by Alican Kiraz
|
| 22 |
+
|
| 23 |
+
[](https://tr.linkedin.com/in/alican-kiraz)
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
Links:
|
| 28 |
+
- Medium: https://alican-kiraz1.medium.com/
|
| 29 |
+
- Linkedin: https://tr.linkedin.com/in/alican-kiraz
|
| 30 |
+
- X: https://x.com/AlicanKiraz0
|
| 31 |
+
- YouTube: https://youtube.com/@alicankiraz0
|
| 32 |
+
|
| 33 |
+
With the release of the new DeepSeek-R1, I quickly began training SenecaLLM v1.3 based on this model. During training:
|
| 34 |
+
* About 20 hours on BF16 with 4×H200
|
| 35 |
+
* About 10 hours on BF16 with 8×A100
|
| 36 |
+
* About 12 hours on FP32 with 8×H200
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
**It does not pursue any profit.**
|
| 40 |
+
|
| 41 |
+
Thanks to DeepSeek R1’s Turkish support capability and the dataset used in SenecaLLM v1.3, it can now provide Turkish support! With the new dataset I’ve prepared, it can produce quite good outputs in the following areas:
|
| 42 |
+
* Information Security v1.4
|
| 43 |
+
* Incident Response v1.3
|
| 44 |
+
* Threat Hunting v1.3
|
| 45 |
+
* Ethical Exploit Development v1.2
|
| 46 |
+
* Purple Team Tactics v1.2
|
| 47 |
+
* Reverse Engineering v1.0
|
| 48 |
+
|
| 49 |
+
"Those who shed light on others do not remain in darkness..."
|
| 50 |
+
|
| 51 |
+
|
| 52 |
# AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3-Safe-Q8_0-GGUF
|
| 53 |
This model was converted to GGUF format from [`AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3-Safe`](https://huggingface.co/AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3-Safe) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
| 54 |
Refer to the [original model card](https://huggingface.co/AlicanKiraz0/Seneca-x-DeepSeek-R1-Distill-Qwen-32B-v1.3-Safe) for more details on the model.
|