Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
PKU-Alignment
/
alpaca-7b-reproduced
like
5
Follow
PKU-Alignment
48
Safetensors
tatsu-lab/alpaca
English
safe-rlhf
llama
instruction-following
instruction-fine-tuning
supervised-fine-tuning
ift
sft
deepspeed
beaver
alpaca
arxiv:
2302.13971
arxiv:
2310.12773
Model card
Files
Files and versions
Train
main
alpaca-7b-reproduced
/
generation_config.json
XuehaiPan
Convert model checkpoint to safetensors
c3c3c2d
9 months ago
raw
Copy download link
history
blame
Safe
132 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
1
,
"eos_token_id"
:
2
,
"pad_token_id"
:
0
,
"transformers_version"
:
"4.37.2"
}