Instructions to use OfflineBase/Muse-Glimmer-30B-Knowledge-Stage-B-R30-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use OfflineBase/Muse-Glimmer-30B-Knowledge-Stage-B-R30-LoRA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-models/Muse-Glimmer-30B") model = PeftModel.from_pretrained(base_model, "OfflineBase/Muse-Glimmer-30B-Knowledge-Stage-B-R30-LoRA") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from OfflineBase/Muse-Glimmer-30B-Knowledge-Stage-B-R30-LoRA: direct link, hf CLI and curl.
- Browser
- Download file 861 Bytes
-
https://huggingface.co/OfflineBase/Muse-Glimmer-30B-Knowledge-Stage-B-R30-LoRA/resolve/main/NOTICE
- Command line
-
hf download hf://OfflineBase/Muse-Glimmer-30B-Knowledge-Stage-B-R30-LoRA/NOTICE
-
curl -L -o NOTICE https://huggingface.co/OfflineBase/Muse-Glimmer-30B-Knowledge-Stage-B-R30-LoRA/resolve/main/NOTICE
861 Bytes
| Muse-Glimmer-30B-Knowledge-Stage-B-R30-LoRA | |
| Copyright 2026 OfflineBase | |
| Built with Muse Spark Open. | |
| This product is a fine-tune of Muse Glimmer 30B (meta-models/Muse-Glimmer-30B, | |
| revision cec94fcfd6512f2cfe708138c32533b346ea4f69), licensed by Meta under the Apache | |
| License, Version 2.0 (see LICENSE). | |
| What we changed: we trained LoRA weights (rank 64) on the language model's projection layers. This repo holds them as a LoRA adapter. | |
| Part of the training data was written by Muse Spark Open, so this model is a Derivative | |
| under the Muse Model License (see MUSE_MODEL_LICENSE.md, Exhibit A: Muse Spark Open Usage | |
| Policy). Use of this model must also follow the Muse Glimmer Usage Policy (USAGE_POLICY.md). | |
| Our modifications are licensed under the Apache License, Version 2.0 (see LICENSE). | |
| This is not an official Meta release and is not endorsed by Meta. | |