Edit model card

SQFT Fine-tuned Model: sqft-mistral-7b-v0.3-50-gptq-gsm8k-heu-adapter

Evaluation

BASE_MODEL_NAME=IntelLabs/sqft-mistral-7b-v0.3-50-base-gptq
ADAPTER_MODEL_NAME=IntelLabs/sqft-mistral-7b-v0.3-50-gptq-gsm8k-heu-adapter
lm_eval --model hf --model_args pretrained=${BASE_MODEL_NAME},peft=${ADAPTER_MODEL_NAME},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.

Model Sources

Citation

@article{munoz2024sqft,
  title = {SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models},
  author={J. Pablo Munoz and Jinjie Yuan and Nilesh Jain},
  journal={},
  year={2024}
}

License

Apache-2.0

Downloads last month
74
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for IntelLabs/sqft-mistral-7b-v0.3-50-gptq-gsm8k-heu-adapter

Adapter
(1)
this model

Dataset used to train IntelLabs/sqft-mistral-7b-v0.3-50-gptq-gsm8k-heu-adapter

Collection including IntelLabs/sqft-mistral-7b-v0.3-50-gptq-gsm8k-heu-adapter