id string | source string | tools string | messages string | num_tokens int64 | meta string |
|---|---|---|---|---|---|
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_351977 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "get_pokemon_move_info", "description": "Retrieves information about a Pokémon's move using the PokéAPI.", "parameters": {"type": "object", "properties": {"pokemon_name": {"description": "The name of the Pokémon.", "type": "string", "default": "run"}, "move_name": {"descriptio... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,321 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_736263 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "get_all_predictions", "description": "Fetches all betting tips from the API with configurable parameters for connection, content type, sorting, and API key.", "parameters": {"type": "object", "properties": {"connection": {"description": "Specifies the connection type for the ... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 2,964 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_24028 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "module_name.tournament_teams", "description": "Fetches the list of teams participating in a specific tournament using the provided tournament ID and RapidAPI key.", "parameters": {"type": "object", "properties": {"tournamentid": {"description": "The ID of the tournament for w... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,298 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_T2_285929 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "top_headlines", "description": "Fetches top headline news articles based on specified parameters.", "parameters": {"type": "object", "properties": {"language": {"description": "Language code to filter news articles. Default is 'en'. Options include:", "type": "string", "defau... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,713 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_T2_82628 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "treeequivalent", "description": "Calculate the number of trees required to create a given weight of paper.", "parameters": {"type": "object", "properties": {"weight": {"description": "The weight of the paper.", "type": "string", "default": "200"}, "unit": {"description": "The... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,229 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_437537 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "elhighlights.fetch", "description": "Fetches football highlights from a specified API endpoint.", "parameters": {"type": "object", "properties": {"url": {"description": "The API endpoint URL for fetching highlights. Defaults to 'https://acrtadeon.elhighlights.com/embed/0nvR19... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 831 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_517835 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "create_histogram", "description": "Create a histogram based on provided data.", "parameters": {"type": "object", "properties": {"data": {"description": "The data for which histogram needs to be plotted.", "type": "array", "default": 10}, "bins": {"description": "The number of... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,305 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_492812 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "hotel_module.is_hotel_available", "description": "Checks the availability of a hotel for a given date range.", "parameters": {"type": "object", "properties": {"hotel": {"description": "The name of the hotel.", "type": "string"}, "city": {"description": "The city where the hot... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 2,413 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_600117 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "trending_videos", "description": "Fetches a list of trending YouTube videos based on the given parameters.", "parameters": {"type": "object", "properties": {"country": {"description": "The country code for which to retrieve trending videos. Defaults to 'us'.", "type": "string... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 2,134 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_292444 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "province", "description": "Fetches the average price of gas in a specific province in Canada using the Canadian Gas Prices API.", "parameters": {"type": "object", "properties": {"province": {"description": "A valid province name in Canada. Options include Ontario, Quebec, Alb... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 914 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_249414 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "gettotalsolved", "description": "Fetches the total number of questions solved by the given LeetCode user.", "parameters": {"type": "object", "properties": {"username": {"description": "The LeetCode username of the user whose solved questions are to be retrieved.", "type": "st... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,275 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_57984 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "is_leap_year", "description": "Checks if a year is a leap year.", "parameters": {"type": "object", "properties": {"year": {"description": "The year to check.", "type": "integer"}}}}}, {"type": "function", "function": {"name": "predict_forest_area", "description": "Predicts th... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,242 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_31625 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "cosine_similarity", "description": "Calculates the cosine similarity between two vectors.", "parameters": {"type": "object", "properties": {"vector_a": {"description": "The first vector.", "type": "array", "items": {"type": "number"}}, "vector_b": {"description": "The second ... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,576 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_669349 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "shazam.auto_complete", "description": "Fetch autocomplete suggestions for a given term using the Shazam API.", "parameters": {"type": "object", "properties": {"term": {"description": "The word or phrase to get suggestions for (e.g., song title, artist name).", "type": "string... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 681 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_434004 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "user.user_followers_list", "description": "Fetches the list of followers for a TikTok user using the provided API parameters.", "parameters": {"type": "object", "properties": {"fresh": {"description": "If set to 1, forces the API to return fresh data instead of cached data. D... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,624 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_866983 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "media.hashtag_feed_video_posts_v2", "description": "Fetches video posts related to a specific hashtag from a social media platform, providing metadata such as direct URLs, statistics, and more.", "parameters": {"type": "object", "properties": {"name": {"description": "Hashtag... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,715 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_323905 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "get_one_anime_by_ranking", "description": "Fetches the details of an anime based on its ranking from the Anime DB API.", "parameters": {"type": "object", "properties": {"rank": {"description": "The ranking position of the desired anime.", "type": "integer", "default": "1"}}}}... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 810 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_399980 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "reverse_search_by_image", "description": "Perform a reverse image search using a specified image URL and return the search results.", "parameters": {"type": "object", "properties": {"url": {"description": "The URL of the image to search by.", "type": "string", "default": "htt... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 980 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_335834 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "CNPJ Search", "description": "Search for company data by CNPJ", "parameters": {"type": "object", "properties": {"cnpj": {"description": "The CNPJ number of the company", "type": "string", "default": ""}}}}}, {"type": "function", "function": {"name": "Consumer Name Search API"... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 2,515 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_231268 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "fibonacci", "description": "Calculates the nth Fibonacci number.", "parameters": {"type": "object", "properties": {"n": {"description": "The position of the Fibonacci number.", "type": "integer"}}}}}, {"type": "function", "function": {"name": "is_palindrome", "description": "... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 898 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_848886 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "event_data", "description": "Fetches event data for a given event ID using the Toolbench RapidAPI.", "parameters": {"type": "object", "properties": {"event_id": {"description": "The unique identifier for the event.", "type": "integer", "default": "10277254"}}}}}, {"type": "fu... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,087 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_786754 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "token_forwarding.get_token_forwarding_wallets", "description": "Fetches a list of token forwarding wallets from the RapidAPI Token Forwarding service.", "parameters": {"type": "object", "properties": {"is_id": {"description": "Identifier for the token forwarding wallet. Defau... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 816 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_T2_90541 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "titles.new_titles", "description": "Fetches a listing of new title IDs added to Watchmode within a specific date range.", "parameters": {"type": "object", "properties": {"page": {"description": "Specifies the page of results to return. Defaults to 1.", "type": "integer", "def... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,252 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_T2_69157 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "advanced", "description": "Fetches advanced chess puzzles based on various search criteria from an external API.", "parameters": {"type": "object", "properties": {"number_of_puzzles": {"description": "Number of puzzles to fetch. Defaults to 1.", "type": "integer", "default": ... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,341 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_254620 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "menudetails", "description": "Fetch menu details using a given menu ID and language preference.", "parameters": {"type": "object", "properties": {"is_id": {"description": "The ID of the menu whose details are to be fetched.", "type": "string", "default": "5a76c927bb5d660001e0... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 751 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_T2_91271 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "airplane.get_airplane_details", "description": "Fetches details of an airplane using the provided code.", "parameters": {"type": "object", "properties": {"code": {"description": "The unique identifier of the airplane to fetch details for.", "type": "string", "default": "777"}... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,106 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_603457 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "get_the_latest_remote_jobs", "description": "Fetches the latest 20 remote job listings from a specified company and/or category using the RapidAPI.", "parameters": {"type": "object", "properties": {"company": {"description": "The company name to filter job listings (default i... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 2,415 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_165209 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "spotify.get_user_playlists", "description": "Fetch all public playlists of a specific user from the Spotify API.", "parameters": {"type": "object", "properties": {"user_id": {"description": "The ID of the user whose playlists are to be fetched.", "type": "string", "default": ... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,638 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_543865 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "video_post_comments", "description": "Fetches comments for a specified video post from the TikTok API.", "parameters": {"type": "object", "properties": {"video_id": {"description": "The ID of the video for which to fetch comments.", "type": "string", "default": "7137423965982... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 813 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_T2_142227 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "feedbacks_id", "description": "Fetches feedbacks for a given product ID from the AliExpress unofficial API.", "parameters": {"type": "object", "properties": {"is_id": {"description": "The product ID for which feedbacks are to be fetched.", "type": "integer", "default": "40008... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,184 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_244053 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "whole_foods.whole_foods_order", "description": "Places an order at Whole Foods.", "parameters": {"type": "object", "properties": {"store_location": {"description": "The location of the Whole Foods store.", "type": "string"}, "item_list": {"description": "A list of items to or... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 811 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_T2_99404 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "get_ip_zipcode", "description": "Retrieves the ZIP code of a given IP address using the ip-api.com API.", "parameters": {"type": "object", "properties": {"ip": {"description": "The IP address to locate.", "type": "string"}}}}}, {"type": "function", "function": {"name": "proje... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,019 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_695708 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "pokemon.get_pokemon_data_by_name", "description": "Fetches data for a specified Pokemon using its name from the Pokemon Unite API.", "parameters": {"type": "object", "properties": {"name": {"description": "The name of the Pokemon for which data is to be fetched.", "type": "st... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 1,661 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_565184 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "match", "description": "Fetch the detailed information of an individual tennis match using the provided match ID from the Tennis Live Data API.", "parameters": {"type": "object", "properties": {"match_id": {"description": "The unique identifier for the tennis match to retriev... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 2,880 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated_S2_708867 | allenai/Dolci-Instruct-SFT-Tool-Use | [{"type": "function", "function": {"name": "generate_random_string", "description": "Generates a random string of specified length and character types.", "parameters": {"type": "object", "properties": {"length": {"description": "The length of the random string.", "type": "integer", "default": true}, "uppercase": {"desc... | [{"role": "system", "content": "You are a helpful function-calling AI assistant. You are provided with function signatures within <functions></functions> XML tags. You may call one or more functions to assist with the user query. Output any function calls within <function_calls></function_calls> XML tags. Don't make as... | 571 | {"dataset_source": "allenai/olmo-toolu-sft-mix-T2-S2-f2-bfclv3-decontaminated", "file": "train-00000-of-00006.parquet"} |
End of preview. Expand in Data Studio
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
SFT Agent Collection
This dataset is a curated mixture of agentic / tool-use / terminal SFT data, all converted into a unified messages+tools format.
Dataset Summary
| Dataset | Source | Raw Samples | Filtered Samples | Parquet Size | Avg Tokens |
|---|---|---|---|---|---|
| Dolci-Instruct-SFT-Tool-Use | allenai/Dolci-Instruct-SFT-Tool-Use | 227,579 | 122,410 | 205 MB | 3,265 |
| Dolci-Think-SFT-7B | allenai/Dolci-Think-SFT-7B | 2,253,604 | 2,253,600 | 24 GB | 11,152 |
| LiteCoder-Terminal-SFT | Lite-Coder/LiteCoder-Terminal-SFT | 11,255 | 11,150 | 166 MB | 30,606 |
| Nemotron-SFT-Agentic-v2 | nvidia/Nemotron-SFT-Agentic-v2 | 47,602 | 47,602 | 243 MB | 6,930 |
| Nemotron-Terminal-Corpus | nvidia/Nemotron-Terminal-Corpus | 139,841 | 57,405 | 636 MB | 16,010 |
| Open-SWE-Traces | Open-SWE-Traces | 207,489 | 156,543 | 5.5 GB | 70,156 |
| SWE-smith-trajectories | SWE-bench/SWE-smith-trajectories | 26,076 | 25,953 | 590 MB | 34,249 |
| ToolMind | modelscope/ToolMind | 368,611 | 296,107 | 561 MB | 2,583 |
| xlam-function-calling-60k | Salesforce/xlam-function-calling-60k | 101,363 | 71,896 | 80 MB | 1,267 |
| Total | 3,383,454 | 3,042,666 | 31.5 GB | 13,096 |
- Filter threshold: samples with
num_tokens > 128,000were removed (6,880 samples dropped). - Tokenizer:
Qwen/Qwen2.5-7Bwas used for token counting.
Schema
Each row in the parquet files contains the following columns:
| Column | Type | Description |
|---|---|---|
id |
string | Unique sample identifier |
source |
string | Original dataset source |
tools |
string | JSON-serialized list of tool definitions |
messages |
string | JSON-serialized conversation messages |
num_tokens |
int64 | Total token count of the sample |
meta |
string | JSON-serialized original metadata |
Nested fields (tools, messages, meta) are stored as JSON strings to keep a consistent schema across heterogeneous sources.
Message Format
Messages follow the standard chat format:
system: system prompt, usually contains tool definitionsuser: user inputassistant: model response, may includetool_callstool: tool execution results, referencestool_call_id
Example tool call structure:
{
"role": "assistant",
"content": "",
"tool_calls": [
{
"id": "call_xxx",
"type": "function",
"function": {
"name": "get_weather",
"arguments": "{\"city\": \"Beijing\"}"
}
}
]
}
Loading Example
import pyarrow.parquet as pq
import json
table = pq.read_table("Dolci-Think-SFT-7B.parquet")
messages = json.loads(table.column("messages")[0].as_py())
tools = json.loads(table.column("tools")[0].as_py())
Processing Pipeline
- Download: raw datasets were downloaded from Hugging Face mirrors where network was unstable.
- Phase 1 EDA: small-sample analysis to understand schema, tool usage, and message patterns.
- Phase 2 Conversion: each dataset was converted to the unified format with
toolsandmessages. - Token counting:
num_tokenscomputed withQwen/Qwen2.5-7Btokenizer. - Filtering: removed samples exceeding 128k tokens to fit common context windows.
- Parquet compression: jsonl files were serialized to parquet with zstd compression for efficient storage.
Notes
SWE-smith-trajectoriesraw token statistics count conversation messages only; patch fields (git diffs) are excluded because some exceed 100k tokens and are not part of the model input sequence.Open-SWE-Tracescontributed the majority of dropped long-context samples due to its trajectory format.- Some malformed JSON lines in
Nemotron-SFT-Agentic-v2were skipped during conversion.
- Downloads last month
- 330