GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
apple
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
apple
Model Tree
mistralai/Mixtral-8x7B-Instruct-v0.1
Input Modalities
Output Modalities
Supported Functionality
bibtex
@misc{zhang2025sage, title = {SAGE: Steering and Refining Dialogue Generation with State‑Action Augmentation}, author = {Zhang, Yizhe and Jaitly, Navdeep}, year = {2025}, howpublished = {arXiv preprint}, note = {arXiv:2503.03040}}📄 Paper: Available on arXiv and Papers with Code
SAGE introduces latent state-action variables between dialogue turns, enabling:
This approach allows for more nuanced and contextually appropriate dialogue generation compared to traditional methods.
Base Model: Mixtral-8x7B-Instruct
Training Pipeline:
SAGE demonstrates significant improvements on emotional-intelligence metrics compared to baseline models while maintaining generative flexibility and coherence. The model shows particular strength in:
bash
git clone https://github.com/apple/ml-sage-dialog-gencd ml-sage-dialog-genbash setup.shpython
from transformers import AutoTokenizer, AutoModelForCausalLM # Load the modeltokenizer = AutoTokenizer.from_pretrained("apple/sage-dialogue-gen")model = AutoModelForCausalLM.from_pretrained("apple/sage-dialogue-gen") # Generate dialogueinput_text = "I'm feeling overwhelmed with work lately."inputs = tokenizer(input_text, return_tensors="pt")outputs = model.generate(**inputs, max_length=150, do_sample=True, temperature=0.7)response = tokenizer.decode(outputs[0], skip_special_tokens=True)requirements.txtContributions are welcome! Please see our contributing guidelines and code of conduct before submitting pull requests.
This project is licensed under the Apache License 2.0. See the LICENSE file for details.
For questions or issues, please open a GitHub issue or contact the development team through the official Apple ML research channels.
@misc{zhang2025sage, title = {SAGE: Steering and Refining Dialogue Generation with State‑Action Augmentation}, author = {Zhang, Yizhe and Jaitly, Navdeep}, year = {2025}, howpublished = {arXiv preprint}, note = {arXiv:2503.03040}}git clone https://github.com/apple/ml-sage-dialog-gencd ml-sage-dialog-genbash setup.shfrom transformers import AutoTokenizer, AutoModelForCausalLM # Load the modeltokenizer = AutoTokenizer.from_pretrained("apple/sage-dialogue-gen")model = AutoModelForCausalLM.from_pretrained("apple/sage-dialogue-gen") # Generate dialogueinput_text = "I'm feeling overwhelmed with work lately."inputs = tokenizer(input_text, return_tensors="pt")outputs = model.generate(**inputs, max_length=150, do_sample=True, temperature=0.7)response = tokenizer.decode(outputs[0], skip_special_tokens=True)