Instructions to use OfflineBase/Muse-Glimmer-30B-Lab-Moss-Run2-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use OfflineBase/Muse-Glimmer-30B-Lab-Moss-Run2-LoRA with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Muse-Glimmer-30B-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "OfflineBase/Muse-Glimmer-30B-Lab-Moss-Run2-LoRA") - Notebooks
- Google Colab
- Kaggle
Muse Glimmer 30B lab adapter (job 83d71f74)
Run 2 of the lab's Glimmer recipe, on the made-up Zubrelian moss guide. The BUILD_LOG calls it an adapter from an older base, used as a pipeline test. This repo is private. Nothing here has had the license and personal-data review that a public release needs.
LoRA r=16 on unsloth/Muse-Glimmer-30B-unsloth-bnb-4bit.
Data
Made-up. Its dataset's rows are not in this repo.
Measured
Used in a one-bit pipeline test with text it didn't train on: IQ1_S KL 1.1827, 19 of 30 final answers, left out by the gates. That says nothing about this adapter on its own topic.
Not run on a Jetson in any log we have.
License
Fine-tune of Muse Glimmer 30B through Unsloth's 4-bit build, unsloth/Muse-Glimmer-30B-unsloth-bnb-4bit. Meta releases Muse Glimmer 30B under the Apache License 2.0 (LICENSE). Use must follow the Muse Glimmer Usage Policy (USAGE_POLICY.md), which says the model is not meant for people under 18 and bars presenting outputs as written by a person.
Not an official Meta release. Meta has not reviewed or endorsed it. No warranty.
- Downloads last month
- 5
Model tree for OfflineBase/Muse-Glimmer-30B-Lab-Moss-Run2-LoRA
Base model
meta-models/Muse-Glimmer-30B