saily-13b-v0 / README.md
deepnight-research's picture
Update README.md
fee0887
---
license: other
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- 7B
- Saily
- DEEPNIGHT
- Llama
- Llama2
---
# SaiLy 7B (deepnight-research/saily-7b-v0)
<img src="https://i.ibb.co/TvZQjZM/Leonardo-Diffusion-XL-Furious-and-strong-Elephant-and-anchor-l-1.jpg" alt="Saily: Experimental AI Models by DEEPNIGHT">
---
### SaiLy is a series/collection of AI Models by DEEPNIGHT-RESEARCH which are highly experimental and uncensored. Please use with responsibility.
---
<br>
Prompt Template: Alpeca
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
### Description
This is the first model of the series. The model is based on Llama2-chat.
---
### Did some said CODE?
Here you go!
```python
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'deepnight-research/saily-7b-v0'
)
```
To use the optimized triton implementation of FlashAttention, you can load the model on GPU ```(cuda:0)``` with ```attn_impl='triton'``` and with ```bfloat16``` precision:
```python
import torch
import transformers
name = 'deepnight-research/saily-7b-v0'
config = transformers.AutoConfig.from_pretrained(name)
config.attn_config['attn_impl'] = 'triton'
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
torch_dtype=torch.bfloat16, # Load model weights in bfloat16
trust_remote_code=True
)
```
---
If you would like to support us, please [consider donating](https://donate.deepnight.tech) for [#aiforcause](https://github.com/deepnight-ai/aiforcause).
Cheers✌️
- Team [DEEPNIGHT](https://deepnight.tech)