jpablomch
/

sqft-sparsepeft-llama-3-8b-50-gsm8k-heu

Model card Files Files and versions Community

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models

Base Model: IntelLabs/sqft-llama-3-8b-50-base
Sparsity: 50%
Quantization: No
Finetune Method: SQFT + SparsePEFT
Finetune data: GSM8K
Sub-Adapter: Heuristic

Evaluation

MODEL_PATH=IntelLabs/sqft-sparsepeft-llama-3-8b-50-gsm8k-heu
lm_eval --model hf --model_args pretrained=${MODEL_PATH},add_bos_token=True,trust_remote_code=True --tasks gsm8k --batch_size auto:4

Refer to our repo for the environment information to run this command.

Downloads last month: 5

Safetensors

Model size

8.03B params

Tensor type

FP16

·

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.