Saily_
Collection
These models are experimental. Most of them are uncensored. Please use with responsibility.
•
5 items
•
Updated
•
1
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
This is the first stable model of the series. The model is based on Llama2-chat.
Here you go!
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'deepnight-research/saily_100B'
)
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:
import torch
import transformers
name = 'deepnight-research/saily_100B'
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 for #aiforcause.
Cheers✌️