README.md

metadata

language:
  - en
license: apache-2.0
model-index:
  - name: luxia-21.4b-alignment-v1.0
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 36.93
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 48.02
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 6.19
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 6.82
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 12.51
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 26.7
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=saltlux/luxia-21.4b-alignment-v1.0
          name: Open LLM Leaderboard

Introduction

We introduce luxia-21.4b-alignment-v1.0, an instruction-tuned and alignment model based on luxia-21.4b. Please refer to the evaluation results table for details.

Instruction Fine-tuning Strategy

We utilize state-of-the-art instruction fine-tuning methods including supervised fine-tuning (SFT) and direct preference optimization (DPO)

Data Contamination Test Results

Results will be updated soon.

Evaluation Results

Results will be updated soon.

Usage Instructions

How to use

# pip install transformers==4.35.2
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("saltlux/luxia-21.4b-alignment-v0.1")
model = AutoModelForCausalLM.from_pretrained(
    "saltlux/luxia-21.4b-alignment-v0.1",
    device_map="auto",
    torch_dtype=torch.float16,
)

License

• saltlux/luxia-21.4b-alignment-v1.0: apache-2.0

Contact Us

Any questions and suggestions are welcomed at the discussion tab.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	22.86
IFEval (0-Shot)	36.93
BBH (3-Shot)	48.02
MATH Lvl 5 (4-Shot)	6.19
GPQA (0-shot)	6.82
MuSR (0-shot)	12.51
MMLU-PRO (5-shot)	26.70