Hugging Face's logo

ContextualAI
/
archangel_sft-ppo_pythia2-8b

Text Generation
Transformers
Safetensors
English
gpt_neox
human feedback
rlhf
preferences
alignment
HALO
halos
dpo
rl
text-generation-inference
Inference Endpoints
Model card Files Community
xwinxu commited on
Commit
45d3782
•
1 Parent(s): b7dc4d5

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -1,8 +1,8 @@
1
- ![halos](assets/thumbnail.jpg)
2
 
3
  This repo contains the model checkpoints for:
4
- - model family pythia2-8b
5
- - optimized with the loss sft+ppo
6
  - aligned using the SHP, Anthropic HH and Open Assistant datasets.
7
 
8
  Please refer to our code repository which contains intructions for training your own HALOs and links to our model cards.
 
1
+ ![halos](https://gist.github.com/assets/29318529/fe2d8391-dbd1-4b7e-9dc4-7cb97e55bc06)
2
 
3
  This repo contains the model checkpoints for:
4
+ - model family <b>pythia2-8b</b>
5
+ - optimized with the loss <b>SFT+PPO</b>
6
  - aligned using the SHP, Anthropic HH and Open Assistant datasets.
7
 
8
  Please refer to our code repository which contains intructions for training your own HALOs and links to our model cards.