AIM Merged Checkpoints (With AIM)
Collection
The full set of checkpoints merged and with AIM applied, used in Activation Informed Merging (AIM) merging paper experiments.
•
21 items
•
Updated
AIM Paper Checkpoints Uploaded For Replication
This repository includes one of the checkpoints used in the paper "Activation-Informed Merging of Large Language Models". Specifics of this model are as follows:
- Merging Method: dare_ties
- Models Used In Merging
- Base Model: unsloth/llama-2-13b
- Math: vanillaOVO/WizardMath-13B-V1.0
- Instruction Tuned: WizardLMTeam/WizardLM-13B-V1.2
- AIM: True
Benchmark results and paper details can be found at the official GitHub.
- Downloads last month
- 14
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.
Model tree for ahn1376/DARETies___Math-Instruction_Tuned___AIM
Merge model
this model