Reinforcement Learning
Transformers
Safetensors
English
llama
text-generation
Llama-3
RL
Atropos
Tool Calling
Nous Research
instruct
finetune
reasoning
function calling
json mode
chatml
text-generation-inference
Instructions to use NousResearch/DeepHermes-AscensionMaze-RLAIF-8b-Atropos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NousResearch/DeepHermes-AscensionMaze-RLAIF-8b-Atropos with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("NousResearch/DeepHermes-AscensionMaze-RLAIF-8b-Atropos") model = AutoModelForCausalLM.from_pretrained("NousResearch/DeepHermes-AscensionMaze-RLAIF-8b-Atropos") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 3193165bd37536da0250eb70cc3d1896c44875c8899eb5180bdec470ecbcf7f2
- Size of remote file:
- 5 GB
- SHA256:
- 1e77ef7ebd86b8ca99396066877bdd3ed4ca98c1c0f02bd12fadac115a9e176e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.