metadata
license: cc-by-nc-4.0
model-index:
- name: Lelantos-DPO-7B
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: 71.08
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Lelantos-DPO-7B
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: 87.22
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Lelantos-DPO-7B
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: 64
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Lelantos-DPO-7B
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: 67.77
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Lelantos-DPO-7B
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: 80.03
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Lelantos-DPO-7B
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: 68.46
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=SanjiWatsuki/Lelantos-DPO-7B
name: Open LLM Leaderboard
Model | AGIEval | GPT4All | TruthfulQA | Bigbench | Average |
---|---|---|---|---|---|
Lelantos-DPO-7B | 45.47 | 75 | 67.05 | 46.64 | 58.54 |
Lelantos-7B | 46.01 | 75 | 64.93 | 46.21 | 58.04 |
AGIEval
Task | Version | Metric | Value | Stderr | |
---|---|---|---|---|---|
agieval_aqua_rat | 0 | acc | 25.20 | ± | 2.73 |
acc_norm | 24.02 | ± | 2.69 | ||
agieval_logiqa_en | 0 | acc | 40.71 | ± | 1.93 |
acc_norm | 40.25 | ± | 1.92 | ||
agieval_lsat_ar | 0 | acc | 24.35 | ± | 2.84 |
acc_norm | 23.04 | ± | 2.78 | ||
agieval_lsat_lr | 0 | acc | 55.69 | ± | 2.20 |
acc_norm | 55.49 | ± | 2.20 | ||
agieval_lsat_rc | 0 | acc | 65.06 | ± | 2.91 |
acc_norm | 65.43 | ± | 2.91 | ||
agieval_sat_en | 0 | acc | 76.70 | ± | 2.95 |
acc_norm | 76.70 | ± | 2.95 | ||
agieval_sat_en_without_passage | 0 | acc | 47.09 | ± | 3.49 |
acc_norm | 45.63 | ± | 3.48 | ||
agieval_sat_math | 0 | acc | 36.36 | ± | 3.25 |
acc_norm | 33.18 | ± | 3.18 |
Average: 45.47%
GPT4All
Task | Version | Metric | Value | Stderr | |
---|---|---|---|---|---|
arc_challenge | 0 | acc | 62.12 | ± | 1.42 |
acc_norm | 63.23 | ± | 1.41 | ||
arc_easy | 0 | acc | 85.40 | ± | 0.72 |
acc_norm | 81.02 | ± | 0.80 | ||
boolq | 1 | acc | 87.25 | ± | 0.58 |
hellaswag | 0 | acc | 67.97 | ± | 0.47 |
acc_norm | 85.48 | ± | 0.35 | ||
openbookqa | 0 | acc | 36.80 | ± | 2.16 |
acc_norm | 47.20 | ± | 2.23 | ||
piqa | 0 | acc | 81.88 | ± | 0.90 |
acc_norm | 83.57 | ± | 0.86 | ||
winogrande | 0 | acc | 77.27 | ± | 1.18 |
Average: 75.0%
TruthfulQA
Task | Version | Metric | Value | Stderr | |
---|---|---|---|---|---|
truthfulqa_mc | 1 | mc1 | 49.94 | ± | 1.75 |
mc2 | 67.05 | ± | 1.53 |
Average: 67.05%
Bigbench
Task | Version | Metric | Value | Stderr | |
---|---|---|---|---|---|
bigbench_causal_judgement | 0 | multiple_choice_grade | 58.95 | ± | 3.58 |
bigbench_date_understanding | 0 | multiple_choice_grade | 64.23 | ± | 2.50 |
bigbench_disambiguation_qa | 0 | multiple_choice_grade | 36.43 | ± | 3.00 |
bigbench_geometric_shapes | 0 | multiple_choice_grade | 23.68 | ± | 2.25 |
exact_str_match | 3.90 | ± | 1.02 | ||
bigbench_logical_deduction_five_objects | 0 | multiple_choice_grade | 33.40 | ± | 2.11 |
bigbench_logical_deduction_seven_objects | 0 | multiple_choice_grade | 24.43 | ± | 1.63 |
bigbench_logical_deduction_three_objects | 0 | multiple_choice_grade | 54.33 | ± | 2.88 |
bigbench_movie_recommendation | 0 | multiple_choice_grade | 52.20 | ± | 2.24 |
bigbench_navigate | 0 | multiple_choice_grade | 52.70 | ± | 1.58 |
bigbench_reasoning_about_colored_objects | 0 | multiple_choice_grade | 69.65 | ± | 1.03 |
bigbench_ruin_names | 0 | multiple_choice_grade | 50.22 | ± | 2.36 |
bigbench_salient_translation_error_detection | 0 | multiple_choice_grade | 40.98 | ± | 1.56 |
bigbench_snarks | 0 | multiple_choice_grade | 72.38 | ± | 3.33 |
bigbench_sports_understanding | 0 | multiple_choice_grade | 73.23 | ± | 1.41 |
bigbench_temporal_sequences | 0 | multiple_choice_grade | 39.90 | ± | 1.55 |
bigbench_tracking_shuffled_objects_five_objects | 0 | multiple_choice_grade | 20.88 | ± | 1.15 |
bigbench_tracking_shuffled_objects_seven_objects | 0 | multiple_choice_grade | 17.60 | ± | 0.91 |
bigbench_tracking_shuffled_objects_three_objects | 0 | multiple_choice_grade | 54.33 | ± | 2.88 |
Average: 46.64%
Average score: 58.54%
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 73.09 |
AI2 Reasoning Challenge (25-Shot) | 71.08 |
HellaSwag (10-Shot) | 87.22 |
MMLU (5-Shot) | 64.00 |
TruthfulQA (0-shot) | 67.77 |
Winogrande (5-shot) | 80.03 |
GSM8k (5-shot) | 68.46 |