README.md

metadata

license: apache-2.0
model-index:
  - name: Sheared-LLaMA-2.7B-ShareGPT
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 41.04
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 71.26
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 28.5
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 47.71
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 64.17
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 0
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT
          name: Open LLM Leaderboard

Paper: https://arxiv.org/pdf/2310.06694.pdf
Code: https://github.com/princeton-nlp/LLM-Shearing
Models: Sheared-LLaMA-1.3B, Sheared-LLaMA-2.7B

Training information

This is the instruction tuned version of princeton-nlp/Sheared-LLaMA-2.7B. We trained the base model on 10,000 instruction-response pairs sampled from the ShareGPT dataset (first-turns only). We use the following prompt to perform instruction tuning.

You are a helpful assistant. Write a response that appropriately completes the request.\n\n### Input:\n{input}\n\n### Response:

This model can be loaded through transformers.LlamaModelForCausalLM as follows:

from transformers import LlamaModelForCausalLM
model = LlamaModelForCausalLM.from_pretrained("princeton-nlp/Sheared-LLaMA-1.3B-ShareGPT")

Bibtex

If you find our model useful, consider citing us with:

@article{xia2023sheared,
  title={Sheared llama: Accelerating language model pre-training via structured pruning},
  author={Xia, Mengzhou and Gao, Tianyu and Zeng, Zhiyuan and Chen, Danqi},
  journal={arXiv preprint arXiv:2310.06694},
  year={2023}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	42.11
AI2 Reasoning Challenge (25-Shot)	41.04
HellaSwag (10-Shot)	71.26
MMLU (5-Shot)	28.50
TruthfulQA (0-shot)	47.71
Winogrande (5-shot)	64.17
GSM8k (5-shot)	0.00