Galactic Reasoning - Galactica with Chain-Of-Thought
Collection
A collection of the Galactic Reasoning adapters and GGUFs, finetuned to provide chain of thought and reasoning to Meta's Galactica models. • 2 items • Updated • 1
What is Galactic Reasoning?
The Galactic Reasoning adapters are a collection of LoRA adapters, trained for the various sizes of the Facebook/Galactica models. These LoRAs enable the OPT architecture based Galactica models to use reasoning, inspired by more modern models like DeepSeek and OpenAI's O3. To achieve this, the glaiveai/reasoning-v1-20m dataset was used for both training and evalulation of points.
| Size | Parameters | Galactic Reasoning Adapter |
|---|---|---|
mini |
125 M | Coming Soon™ |
base |
1.3 B | In Progress |
standard |
6.7 B | Coming Soon™ |
large |
30 B | Coming Soon™ |
huge |
120 B | Short of a GPU grant, unlikely to happen. |
How were these adapters developed?
These adapters make use of the RS-LoRA finetuning method, trained locally on a Tesla P40. A rank of 64 and an alpha of 32 were utilized. In addition, the following modules were targeted: ""q_proj", "v_proj", "k_proj", "out_proj", "fc1", "fc2"", including FC1 and FC2 due to the OPT architecture.
License
Mozilla Public License 2.0 Modified with CC. See license.md.
Credits
- Credit to Meta/Facebook for the Galactica OPT Based models.
- Credit to GlaiveAi for the reasoning-v1-20m dataset.
- Finally, credit to my highly overworked Tesla P40 who ran for days straight to produce this.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for TitleOS/GalacticReasoning-GGUF
Base model
facebook/galactica-1.3b