Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,7 @@ CyberBase is an experimental *base model* for cybersecurity. (llama-2-13b -> lms
|
|
7 |
|
8 |
# Base cybersecurity model for future fine-tuning, it is not recomended to use on it's own.
|
9 |
- **CyberBase** is a [lmsys/vicuna-13b-v1.5-16k](https://huggingface.co/lmsys/vicuna-13b-v1.5-16k) QLORA fine-tuned on [CyberNative/github_cybersecurity_READMEs](https://huggingface.co/datasets/CyberNative/github_cybersecurity_READMEs) with a single 3090.
|
10 |
-
- It might, therefore,
|
11 |
|
12 |
## Fine-tuning information
|
13 |
- **sequence_len:** 4096 (used during fine-tuning, but should generate up to 16k)
|
|
|
7 |
|
8 |
# Base cybersecurity model for future fine-tuning, it is not recomended to use on it's own.
|
9 |
- **CyberBase** is a [lmsys/vicuna-13b-v1.5-16k](https://huggingface.co/lmsys/vicuna-13b-v1.5-16k) QLORA fine-tuned on [CyberNative/github_cybersecurity_READMEs](https://huggingface.co/datasets/CyberNative/github_cybersecurity_READMEs) with a single 3090.
|
10 |
+
- It might, therefore, inherited [prompt template of FastChat](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md#prompt-template)
|
11 |
|
12 |
## Fine-tuning information
|
13 |
- **sequence_len:** 4096 (used during fine-tuning, but should generate up to 16k)
|