初始化项目,由ModelHub XC社区提供模型
Model: Honkware/Manticore-13b-Landmark Source: Original Platform
This commit is contained in:
21
README.md
Normal file
21
README.md
Normal file
@@ -0,0 +1,21 @@
|
||||
---
|
||||
license: other
|
||||
---
|
||||
# Manticore-13b-Landmark
|
||||
|
||||
## Key Features
|
||||
- **[Landmark Attention](https://arxiv.org/pdf/2305.16300v1.pdf)**
|
||||
- **[Large Context Size (~18k)](https://i.ibb.co/tLLGLNc/image.jpg)**
|
||||
|
||||
## Composition
|
||||
Manticore-13b-Landmark is a blend of:
|
||||
- [Manticore-13B](https://huggingface.co/openaccess-ai-collective/manticore-13b)
|
||||
- [Manticore-13B-Landmark-QLoRA](https://huggingface.co/Honkware/Manticore-13b-Landmark-QLoRA)
|
||||
|
||||
## Using [Oobabooga](https://github.com/oobabooga/text-generation-webui)
|
||||
- Trust Remote Code - **(Enabled)**
|
||||
- Add the bos_token to the beginning of prompts - **(Disabled)**
|
||||
- Truncate the prompt up to this length - **(Increased)**
|
||||
|
||||
## Landmark Training Code
|
||||
See [GitHub](https://github.com/eugenepentland/landmark-attention-qlora) for the training code.
|
||||
Reference in New Issue
Block a user