Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
nicholasKluge
/
Aira-2-124M-DPO
like
1
Text Generation
Transformers
PyTorch
Safetensors
nicholasKluge/instruct-aira-dataset
nicholasKluge/reward-aira-dataset
English
gpt2
alignment
instruction tuned
text generation
conversation
assistant
dpo
Carbon Emissions
text-generation-inference
Inference Endpoints
arxiv:
1803.05457
arxiv:
2109.07958
arxiv:
2203.09509
License:
apache-2.0
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
main
Aira-2-124M-DPO
/
added_tokens.json
nicholasKluge
Upload folder using huggingface_hub
a1e610c
11 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
123 Bytes
{
"<|endofcompletion|>"
:
50258
,
"<|endofinstruction|>"
:
50259
,
"<|pad|>"
:
50260
,
"<|startofinstruction|>"
:
50257
}