Hugging Face's logo

ahn1376
/
WIDEN___Code-Instruction_Tuned___AIM

Safetensors
llama
Merge
Model card Files Community
1

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: WIDEN
  • Models Used In Merging
    • Base Model: unsloth/llama-2-13b
    • Code: layoric/llama-2-13b-code-alpaca
    • Instruction Tuned: WizardLMTeam/WizardLM-13B-V1.2
  • AIM: True

Benchmark results and paper details can be found at the official GitHub.

Downloads last month
6
Safetensors
Model size
13B params
Tensor type
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Model tree for ahn1376/WIDEN___Code-Instruction_Tuned___AIM

WizardLMTeam/WizardLM-13B-V1.2
layoric/llama-2-13b-code-alpaca
unsloth/llama-2-13b
Merge model
this model

Collection including ahn1376/WIDEN___Code-Instruction_Tuned___AIM