forked from JonathanChavezTamales/LLMStats
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
9f85b46
commit fcaf50c
Showing
2 changed files
with
207 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,199 @@ | ||
{ | ||
"canonical_model_id": null, | ||
"fine_tuned_from_model_id": null, | ||
"name": "DeepSeek-V3", | ||
"description": "A powerful Mixture-of-Experts (MoE) language model with 671B total parameters (37B activated per token). Features Multi-head Latent Attention (MLA), auxiliary-loss-free load balancing, and multi-token prediction training. Pre-trained on 14.8T tokens with strong performance in reasoning, math, and code tasks.", | ||
"release_date": "2024-12-25", | ||
"input_context_size": 131072, | ||
"output_context_size": 131072, | ||
"license": "MIT + Model License (Commercial use allowed)", | ||
"multimodal": false, | ||
"web_hydrated": false, | ||
"knowledge_cutoff": null, | ||
"api_ref_link": "https://platform.deepseek.com", | ||
"playground_link": "https://chat.deepseek.com", | ||
"paper_link": "https://github.com/deepseek-ai/DeepSeek-V3/blob/main/DeepSeek_V3.pdf", | ||
"scorecard_blog_link": null, | ||
"repo_link": "https://github.com/deepseek-ai/DeepSeek-V3", | ||
"weights_link": "https://huggingface.co/deepseek-ai/DeepSeek-V3", | ||
"param_count": 671000000000, | ||
"training_tokens": 14800000000000, | ||
"qualitative_metrics": [ | ||
{ | ||
"dataset_name": "MMLU", | ||
"score": 0.885, | ||
"is_self_reported": false, | ||
"analysis_method": "Exact Match", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "MMLU-Redux", | ||
"score": 0.891, | ||
"is_self_reported": false, | ||
"analysis_method": "Exact Match", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "MMLU-Pro", | ||
"score": 0.759, | ||
"is_self_reported": false, | ||
"analysis_method": "Exact Match", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "DROP", | ||
"score": 0.916, | ||
"is_self_reported": false, | ||
"analysis_method": "3-shot F1", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "IF-Eval", | ||
"score": 0.861, | ||
"is_self_reported": false, | ||
"analysis_method": "Prompt Strict", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "GPQA", | ||
"score": 0.591, | ||
"is_self_reported": false, | ||
"analysis_method": "Pass@1", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "SimpleQA", | ||
"score": 0.249, | ||
"is_self_reported": false, | ||
"analysis_method": "Correct", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "FRAMES", | ||
"score": 0.733, | ||
"is_self_reported": false, | ||
"analysis_method": "Accuracy", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "LongBench v2", | ||
"score": 0.487, | ||
"is_self_reported": false, | ||
"analysis_method": "Accuracy", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "HumanEval-Mul", | ||
"score": 0.826, | ||
"is_self_reported": false, | ||
"analysis_method": "Pass@1", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "LiveCodeBench-COT", | ||
"score": 0.405, | ||
"is_self_reported": false, | ||
"analysis_method": "Pass@1-COT", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "LiveCodeBench", | ||
"score": 0.376, | ||
"is_self_reported": false, | ||
"analysis_method": "Pass@1", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "Codeforces", | ||
"score": 0.516, | ||
"is_self_reported": false, | ||
"analysis_method": "Percentile", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "SWE Verified", | ||
"score": 0.42, | ||
"is_self_reported": false, | ||
"analysis_method": "Resolved", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "Aider-Edit", | ||
"score": 0.797, | ||
"is_self_reported": false, | ||
"analysis_method": "Accuracy", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "Aider-Polyglot", | ||
"score": 0.496, | ||
"is_self_reported": false, | ||
"analysis_method": "Accuracy", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "AIME-2024", | ||
"score": 0.392, | ||
"is_self_reported": false, | ||
"analysis_method": "Pass@1", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "MATH-500", | ||
"score": 0.902, | ||
"is_self_reported": false, | ||
"analysis_method": "Exact Match", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "CNMO-2024", | ||
"score": 0.432, | ||
"is_self_reported": false, | ||
"analysis_method": "Pass@1", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "CLUEWSC", | ||
"score": 0.909, | ||
"is_self_reported": false, | ||
"analysis_method": "Exact Match", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "C-Eval", | ||
"score": 0.865, | ||
"is_self_reported": false, | ||
"analysis_method": "Exact Match", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
}, | ||
{ | ||
"dataset_name": "C-SimpleQA", | ||
"score": 0.648, | ||
"is_self_reported": false, | ||
"analysis_method": "Correct", | ||
"date_recorded": "2024-12-25", | ||
"source_link": "https://github.com/deepseek-ai/DeepSeek-V3" | ||
} | ||
] | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters