ContextualAI / archangel_sft-ppo_llama30b

huggingface.co
Total runs: 19
24-hour runs: -3
7-day runs: -2
30-day runs: 1
Model's Last Updated: January 12 2024
text-generation

Introduction of archangel_sft-ppo_llama30b

Model Details of archangel_sft-ppo_llama30b

halos

This repo contains the model checkpoints for:

  • model family llama30b
  • optimized with the loss SFT+PPO
  • aligned using the SHP, Anthropic HH and Open Assistant datasets.

To prompt Archangel models, ensure that the format is consistent with that of TuluV2. For example, a prompt should be formatted as follows, where <|user|> corresponds to the human's role and <|assistant|> corresponds to the LLM's role. The human should speak first:

<|user|>
Hi! I'm looking for a cake recipe.
<|assistant|>
What kind of cake?
<|user|>
Chocolate cake.
<|assistant|>

Note that a beginning-of-sequence (BOS) token is automatically added by all Archangel models during tokenization and does not have to be added by you. No end-of-sequence (EOS) token is added to the prompt.

For models trained with our conditional SFT model, the tokenizers have additional tokens <|good|> and <|bad|> included in the embeddings. To generate with these control tokens in the context, postpend either to the prompt.

Please refer to our code repository or blog which contains intructions for training your own HALOs and links to our model cards.

If you find this repo or the technical paper useful in your research, please feel free to cite our work :

@techreport{ethayarajh2023halos,
  author = {Ethayarajh, Kawin and Xu, Winnie, and Jurafsky, Dan and Kiela, Douwe},
  title = {Human-Centered Loss Functions (HALOs)},
  institution = {Contextual AI},
  note = {https://github.com/ContextualAI/HALOs/blob/main/assets/report.pdf},
  year = {2023},
}

Runs of ContextualAI archangel_sft-ppo_llama30b on huggingface.co

19
Total runs
-3
24-hour runs
-5
3-day runs
-2
7-day runs
1
30-day runs

More Information About archangel_sft-ppo_llama30b huggingface.co Model

More archangel_sft-ppo_llama30b license Visit here:

https://choosealicense.com/licenses/apache-2.0

archangel_sft-ppo_llama30b huggingface.co

archangel_sft-ppo_llama30b huggingface.co is an AI model on huggingface.co that provides archangel_sft-ppo_llama30b's model effect (), which can be used instantly with this ContextualAI archangel_sft-ppo_llama30b model. huggingface.co supports a free trial of the archangel_sft-ppo_llama30b model, and also provides paid use of the archangel_sft-ppo_llama30b. Support call archangel_sft-ppo_llama30b model through api, including Node.js, Python, http.

archangel_sft-ppo_llama30b huggingface.co Url

https://huggingface.co/ContextualAI/archangel_sft-ppo_llama30b

ContextualAI archangel_sft-ppo_llama30b online free

archangel_sft-ppo_llama30b huggingface.co is an online trial and call api platform, which integrates archangel_sft-ppo_llama30b's modeling effects, including api services, and provides a free online trial of archangel_sft-ppo_llama30b, you can try archangel_sft-ppo_llama30b online for free by clicking the link below.

ContextualAI archangel_sft-ppo_llama30b online free url in huggingface.co:

https://huggingface.co/ContextualAI/archangel_sft-ppo_llama30b

archangel_sft-ppo_llama30b install

archangel_sft-ppo_llama30b is an open source model from GitHub that offers a free installation service, and any user can find archangel_sft-ppo_llama30b on GitHub to install. At the same time, huggingface.co provides the effect of archangel_sft-ppo_llama30b install, users can directly use archangel_sft-ppo_llama30b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

archangel_sft-ppo_llama30b install url in huggingface.co:

https://huggingface.co/ContextualAI/archangel_sft-ppo_llama30b

Url of archangel_sft-ppo_llama30b

archangel_sft-ppo_llama30b huggingface.co Url

Provider of archangel_sft-ppo_llama30b huggingface.co

ContextualAI
ORGANIZATIONS

Other API from ContextualAI