metadata

license: llama3.1
datasets:
  - survivi/Llama-3-SynE-Dataset
  - hfl/stem_zh_instruction
  - llamafactory/alpaca_zh
  - llamafactory/alpaca_gpt4_zh
  - hfl/ruozhiba_gpt4
  - codingsteven/Llama-3-8B-chat
language:
  - zh
base_model:
  - meta-llama/Llama-3.1-8B
model-index:
  - name: Control-LLM-Llama3.1-8B-SynE-Concat16-Lerp
    results:
      - task:
          type: pretraining-evaluation
        dataset:
          type: mixed
          name: Pretraining Evaluation Dataset
        metrics:
          - name: exact_match,strict-match (meta_pretrain)
            type: exact_match
            value: 0.458555789246616
            stderr: 0.003519105746208811
            verified: false
          - name: exact_match,strict-match (meta_bbh_3shot_cot_pretrain)
            type: exact_match
            value: 0.6442942712332975
            stderr: 0.005933310420690264
            verified: false
          - name: acc,none (meta_mmlu_5shot_pretrain)
            type: accuracy
            value: 0.6464178891895741
            stderr: 0.004034621567546711
            verified: false
          - name: exact_match,strict-match (meta_mmlu_pro_5shot_pretrain)
            type: exact_match
            value: 0.35804521276595747
            stderr: 0.004370894189453768
            verified: false
      - task:
          type: chinese-evaluation
        dataset:
          type: mixed
          name: Chinese Evaluation Dataset
        metrics:
          - name: exact_match,strict-match (zh_pretrain_multishot)
            type: exact_match
            value: 0.37105507425742573
            stderr: 0.004143191283994466
            verified: false
          - name: acc,none (ceval-valid)
            type: accuracy
            value: 0.5713224368499257
            stderr: 0.01292052444857274
            verified: false
          - name: exact_match,strict-match (ceval-valid-pretrain-cot_zh)
            type: exact_match
            value: 0.34843982169390786
            stderr: 0.01265919137729175
            verified: false
          - name: acc,none (cmmlu)
            type: accuracy
            value: 0.5689000172681747
            stderr: 0.004489346390434928
            verified: false
          - name: exact_match,strict-match (cmmlu_pretrain_cot_zh)
            type: exact_match
            value: 0.37368330167501296
            stderr: 0.00438421288652232
            verified: false

Control-LLM-Llama3.1-8B-SynE-Concat16-Lerp

This is a fine-tuned model of Llama-3.1-8B for muliligual-Chinese tasks on SynE dataset by Control LLM-Concat16-Lerp.

Linked Paper

This model is associated with the paper: Control-LLM.

Evaluation Results

Here is an overview of the evaluation results and findings:

Benchmark Results Table

The table below summarizes evaluation results across Chinese tasks and original capabilities.

Model	CEval	CEvalC	CMMLU	CMMLUC	C-Avg	BBH	MLU	MLUP	O-Avg	Overall
Llama3.1-8B	48.3	12.8	51.1	14.1	13.9	65.2	65.4	35.5	45.9	29.9
Llama-3-SynE	57.7	22.3	57.1	22.8	22.8	61.9	64.0	32.6	42.9	32.9
Full Param Tune	59.0	40.2	60.2	44.3	43.8	64.8	64.9	35.0	45.4	44.6
Stack Expansion	56.0	32.7	55.2	33.4	33.3	62.3	65.6	35.3	44.8	39.1
Concat-Lerp	57.1	34.8	57.0	37.4	37.1	64.4	64.6	35.8	45.9	41.5
Hybrid Expansion	58.9	44.7	57.9	44.3	44.4	65.1	65.7	36.9	46.8	45.6
Control LLM*	57.0	44.7	56.0	44.9	44.8	68.2	65.6	37.9	48.5	46.7

Explanation:

CEval: Chinese Evaluation
CEvalC: Chinese Evaluation (CoT - Chain of Thought)
CMMLU: Chinese MMLU
CMMLUC: Chinese MMLU (CoT)
C-Avg: Chinese - Size Weighted Average across CEval, CEvalC, CMMLU, and CMMLUC
BBH: BigBench Hard
MLU: MMLU (Massive Multitask Language Understanding)
MLUP: MMLU Pro
O-Avg: Original Capability - Size Weighted Average across BBH, MLU, and MLUP
Overall: Combined average across all tasks