Merge branch 'refs/heads/main' into add_rusian_models

# Conflicts:
# all_data_tasks/0/default.jsonl
# all_data_tasks/1/default.jsonl
# all_data_tasks/10/default.jsonl
# all_data_tasks/11/default.jsonl
# all_data_tasks/12/default.jsonl
# all_data_tasks/13/default.jsonl
# all_data_tasks/16/default.jsonl
# all_data_tasks/17/default.jsonl
# all_data_tasks/18/default.jsonl
# all_data_tasks/19/default.jsonl
# all_data_tasks/2/default.jsonl
# all_data_tasks/20/default.jsonl
# all_data_tasks/21/default.jsonl
# all_data_tasks/22/default.jsonl
# all_data_tasks/28/default.jsonl
# all_data_tasks/29/default.jsonl
# all_data_tasks/3/default.jsonl
# all_data_tasks/30/default.jsonl
# all_data_tasks/31/default.jsonl
# all_data_tasks/32/default.jsonl
# all_data_tasks/34/default.jsonl
# all_data_tasks/35/default.jsonl
# all_data_tasks/4/default.jsonl
# all_data_tasks/5/default.jsonl
# all_data_tasks/6/default.jsonl
# all_data_tasks/8/default.jsonl
# all_data_tasks/9/default.jsonl
# boards_data/en/data_overall/default.jsonl
# boards_data/en/data_tasks/Classification/default.jsonl
# boards_data/en/data_tasks/Clustering/default.jsonl
# boards_data/en/data_tasks/PairClassification/default.jsonl
# boards_data/en/data_tasks/Reranking/default.jsonl
# boards_data/en/data_tasks/Retrieval/default.jsonl
# boards_data/en/data_tasks/STS/default.jsonl
# boards_data/en/data_tasks/Summarization/default.jsonl
# boards_data/fr/data_overall/default.jsonl
# boards_data/fr/data_tasks/Classification/default.jsonl
# boards_data/fr/data_tasks/Clustering/default.jsonl
# boards_data/fr/data_tasks/PairClassification/default.jsonl
# boards_data/fr/data_tasks/Reranking/default.jsonl
# boards_data/fr/data_tasks/Retrieval/default.jsonl
# boards_data/fr/data_tasks/STS/default.jsonl
# boards_data/fr/data_tasks/Summarization/default.jsonl
# boards_data/other-cls/data_tasks/Classification/default.jsonl
# boards_data/other-sts/data_tasks/STS/default.jsonl
# boards_data/pl/data_overall/default.jsonl
# boards_data/pl/data_tasks/Classification/default.jsonl
# boards_data/pl/data_tasks/Clustering/default.jsonl
# boards_data/pl/data_tasks/PairClassification/default.jsonl
# boards_data/pl/data_tasks/Retrieval/default.jsonl
# boards_data/pl/data_tasks/STS/default.jsonl
# boards_data/zh/data_overall/default.jsonl
# boards_data/zh/data_tasks/Classification/default.jsonl
# boards_data/zh/data_tasks/Clustering/default.jsonl
# boards_data/zh/data_tasks/PairClassification/default.jsonl
# boards_data/zh/data_tasks/Reranking/default.jsonl
# boards_data/zh/data_tasks/Retrieval/default.jsonl
# boards_data/zh/data_tasks/STS/default.jsonl
# model_meta.yaml

.github/workflows/update_leaderboard.yml

@@ -8,6 +8,7 @@ on:
     - cron: '30 2 * * *'
   push:
     branches: [ main ]
+  workflow_dispatch: # Allows us to trigger the workflow manually via the GitHub UI
 
 jobs:
   build:

model_meta.yaml

@@ -1926,7 +1926,25 @@ models_to_skip:
 - mxs980/b1ade-embed-Q8_0-GGUF
 - chihlunLee/NoInstruct-small-Embedding-v0-Q4_0-GGUF
 - bcastle/snowflake-arctic-embed-l-Q8_0-GGUF
+- niancheng/gte-Qwen2-1.5B-instruct-Q4_K_M-GGUF
+- brtaydin/gte-Qwen2-7B-instruct-Q5_K_M-GGUF
+- yishan-wang/snowflake-arctic-embed-s-Q8_0-GGUF
+- Pekarnick/e5-large-v2-Q4_K_M-GGUF
+- agier9/UAE-Large-V1-Q5_K_S-GGUF
+- archit28/bge-large-en-v1.5-Q4_K_S-GGUF
+- dimcha/mxbai-embed-large-v1-Q4_K_M-GGUF
+- djuna/jina-embeddings-v2-base-en-Q5_K_M-GGUF
+- djuna/jina-embeddings-v2-small-en-Q5_K_M-GGUF
+- djuna/stella-base-en-v2-Q5_K_M-GGUF
+- huoxu/bge-large-en-v1.5-Q8_0-GGUF
+- itod/UAE-Large-V1-Q8_0-GGUF
+- niancheng/gte-Qwen2-7B-instruct-Q4_K_M-GGUF
+- cleatherbury/gte-Qwen2-7B-instruct-Q5_K_M-GGUF
+- niancheng/gte-Qwen2-1.5B-instruct-Q4_K_M-GGUF
+- mxs980/b1ade-embed-Q8_0-GGUF
+- chihlunLee/NoInstruct-small-Embedding-v0-Q4_0-GGUF
 - corto-ai/nomic-embed-text-v1
+- bcastle/snowflake-arctic-embed-l-Q8_0-GGUF
 - Intel/neural-embedding-v1
 cross_encoders:
 - FollowIR-7B

refresh.py

@@ -716,6 +716,8 @@ def load_results(data_path: str) -> list | dict | pd.DataFrame | str | None:
         df = pd.read_json(data_path, orient="records", lines=True)
         if "index" in df.columns:
             df = df.set_index("index")
+        if "Memory Usage (GB, fp32)" in df.columns:
+            df["Memory Usage (GB, fp32)"] = df["Memory Usage (GB, fp32)"].map(lambda value: round(value, 2) if isinstance(value, float) else value)
         return df
 
     else: