Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
The diff you're trying to view is too large. We only load the first 3000 changed files.
Original file line number Diff line number Diff line change
@@ -0,0 +1,107 @@
{
"schema_version": "0.0.1",
"evaluation_id": "hfopenllm_v2/0-hero_Matter-0.2-7B-DPO/1762652579.4626381",
"retrieved_timestamp": "1762652579.462642",
"source_data": [
"https://open-llm-leaderboard-open-llm-leaderboard.hf.space/api/leaderboard/formatted"
],
"evaluation_source": {
"evaluation_source_name": "HF Open LLM v2",
"evaluation_source_type": "leaderboard"
},
"source_metadata": {
"source_organization_name": "Hugging Face",
"evaluator_relationship": "third_party"
},
"model_info": {
"name": "0-hero/Matter-0.2-7B-DPO",
"developer": "0-hero",
"inference_platform": "unknown",
"id": "0-hero/Matter-0.2-7B-DPO"
},
"evaluation_results": [
{
"evaluation_name": "IFEval",
"metric_config": {
"evaluation_description": "Accuracy on IFEval",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.3302792147058693
}
},
{
"evaluation_name": "BBH",
"metric_config": {
"evaluation_description": "Accuracy on BBH",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.3596254301656297
}
},
{
"evaluation_name": "MATH Level 5",
"metric_config": {
"evaluation_description": "Exact Match on MATH Level 5",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.014350453172205438
}
},
{
"evaluation_name": "GPQA",
"metric_config": {
"evaluation_description": "Accuracy on GPQA",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.25922818791946306
}
},
{
"evaluation_name": "MUSR",
"metric_config": {
"evaluation_description": "Accuracy on MUSR",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.381375
}
},
{
"evaluation_name": "MMLU-PRO",
"metric_config": {
"evaluation_description": "Accuracy on MMLU-PRO",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.1163563829787234
}
}
],
"additional_details": {
"precision": "bfloat16",
"architecture": "MistralForCausalLM",
"params_billions": 7.242
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,107 @@
{
"schema_version": "0.0.1",
"evaluation_id": "hfopenllm_v2/01-ai_Yi-1.5-34B-32K/1762652579.463656",
"retrieved_timestamp": "1762652579.463657",
"source_data": [
"https://open-llm-leaderboard-open-llm-leaderboard.hf.space/api/leaderboard/formatted"
],
"evaluation_source": {
"evaluation_source_name": "HF Open LLM v2",
"evaluation_source_type": "leaderboard"
},
"source_metadata": {
"source_organization_name": "Hugging Face",
"evaluator_relationship": "third_party"
},
"model_info": {
"name": "01-ai/Yi-1.5-34B-32K",
"developer": "01-ai",
"inference_platform": "unknown",
"id": "01-ai/Yi-1.5-34B-32K"
},
"evaluation_results": [
{
"evaluation_name": "IFEval",
"metric_config": {
"evaluation_description": "Accuracy on IFEval",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.3118691737922047
}
},
{
"evaluation_name": "BBH",
"metric_config": {
"evaluation_description": "Accuracy on BBH",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.6015685776542417
}
},
{
"evaluation_name": "MATH Level 5",
"metric_config": {
"evaluation_description": "Exact Match on MATH Level 5",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.1540785498489426
}
},
{
"evaluation_name": "GPQA",
"metric_config": {
"evaluation_description": "Accuracy on GPQA",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.36325503355704697
}
},
{
"evaluation_name": "MUSR",
"metric_config": {
"evaluation_description": "Accuracy on MUSR",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.4398229166666667
}
},
{
"evaluation_name": "MMLU-PRO",
"metric_config": {
"evaluation_description": "Accuracy on MMLU-PRO",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.4709109042553192
}
}
],
"additional_details": {
"precision": "bfloat16",
"architecture": "LlamaForCausalLM",
"params_billions": 34.389
}
}
Original file line number Diff line number Diff line change
@@ -0,0 +1,107 @@
{
"schema_version": "0.0.1",
"evaluation_id": "hfopenllm_v2/01-ai_Yi-1.5-34B-Chat-16K/1762652579.464125",
"retrieved_timestamp": "1762652579.4641259",
"source_data": [
"https://open-llm-leaderboard-open-llm-leaderboard.hf.space/api/leaderboard/formatted"
],
"evaluation_source": {
"evaluation_source_name": "HF Open LLM v2",
"evaluation_source_type": "leaderboard"
},
"source_metadata": {
"source_organization_name": "Hugging Face",
"evaluator_relationship": "third_party"
},
"model_info": {
"name": "01-ai/Yi-1.5-34B-Chat-16K",
"developer": "01-ai",
"inference_platform": "unknown",
"id": "01-ai/Yi-1.5-34B-Chat-16K"
},
"evaluation_results": [
{
"evaluation_name": "IFEval",
"metric_config": {
"evaluation_description": "Accuracy on IFEval",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.456449997118756
}
},
{
"evaluation_name": "BBH",
"metric_config": {
"evaluation_description": "Accuracy on BBH",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.6100218256499571
}
},
{
"evaluation_name": "MATH Level 5",
"metric_config": {
"evaluation_description": "Exact Match on MATH Level 5",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.21374622356495468
}
},
{
"evaluation_name": "GPQA",
"metric_config": {
"evaluation_description": "Accuracy on GPQA",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.33808724832214765
}
},
{
"evaluation_name": "MUSR",
"metric_config": {
"evaluation_description": "Accuracy on MUSR",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.43976041666666665
}
},
{
"evaluation_name": "MMLU-PRO",
"metric_config": {
"evaluation_description": "Accuracy on MMLU-PRO",
"lower_is_better": false,
"score_type": "continuous",
"min_score": 0,
"max_score": 1
},
"score_details": {
"score": 0.45445478723404253
}
}
],
"additional_details": {
"precision": "bfloat16",
"architecture": "LlamaForCausalLM",
"params_billions": 34.389
}
}
Loading