messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"role": "system",
"content": "You are a computer science tutor. Explain concepts clearly with examples."
},
{
"role": "user",
"content": "How does modular arithmetic work and why is it useful in computer science?"
},
{
"role": "assistant",
"content": "# Modular Arithmetic\n\n## The... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "Can you research ralph loop proper teqniuqes and implement them here? THe current system is a little buggy\nAssistant action: Bash {\"command\": \"ls /home/user/MythosMini; grep -ril ralph /home/user/MythosMini --include='*' -l | head\", \"description\": \"List repo and find ra... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nq -m \\\"not integration and not slow and not tokenizer_smoke\\\" 2>&1 | tail -3 && uv run ruff check src/teich/studio src/teich/cli.py 2>&1 | tail -5\", \"description\": \"Run full test suite and ruff on new code\", \"timeout\": 600000}\nResult: ========... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that simulates a simple banking transaction system. The function should be able to perform deposit and withdrawal operations on a bank account while considering an overdraft limit. Your function should take in the initial balance, the ove... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a program that checks the existence of files based on a given list of file names. Your program should take a list of file names as input and determine if each file exists in a hypothetical directory. The function should return a list of messages ind... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nout one it survives.\n8\t- R2 Deed type weight: quitclaim deeds are flagged for caution.\n9\t- R3 Priority: liens rank by recording date; tax liens are superior.\n10\t- R4 Latest relevant conveyance drives the Schedule A vesting candidate.\n11\t- R5 E... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Look at some of /home/user/Blindbot/chat_history.json please find interesting ideas. Its being updated live and is currently 9.5mb\nAssistant action: Bash {\"command\": \"ls -la /home/user/Blindbot/chat_history.json && head -c 2000 /home/user/Blindbot/chat_history.json\", \"de... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "Given a list of integers, your task is to convert each integer into its binary representation as a string, where each '1' is represented by a hash symbol '#' and each '0' is represented by a space ' '. The binary representation should be a fixed length of 8 bits (i.e., leading ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that takes a database connection URI as input and extracts the username, password, host, port, and database name from it. The database connection URI will follow the format:<br><br> 'dialect+driver://username:password@host:port/database'.... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with processing user comments to ensure they adhere to community guidelines. Implement a function `process_comment(comment_text)` that takes a string `comment_text` as input and processes it according to the following rules: 1. If the comment contains any offensi... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "Repo: /home/user/MythosMini — a 1,050,241-param byte-level (vocab 257) looped-shared-block transformer trained on fineweb-edu, benchmarked on WikiText-2 byte PPL, BLiMP, ARC-Easy against the Tiny-ML leaderboard (overall = mean of blimp, arc, normalized wiki score; efficiency = ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list of integers `qs` of length `n`. Your task is to find the median of the list and then split the list into two sublists, `a` and `b`, where `a` contains the elements from the beginning of the list up to the median (exclusive), and `b` contains the elements fr... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "[Request interrupted by user]\noops my bad. use deepseek v4 flash on max reasoning\nAssistant action: Bash {\"command\": \"opencode models 2>/dev/null | grep -i deepseek\", \"description\": \"List available deepseek models in opencode\"}\nResult: opencode/deepseek-v4-flash-free... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "Look at some of /home/user/Blindbot/chat_history.json please find interesting ideas. Its being updated live and is currently 9.5mb\nAssistant action: Bash {\"command\": \"ls -la /home/user/Blindbot/chat_history.json && head -c 2000 /home/user/Blindbot/chat_history.json\", \"de... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a concise coding assistant. Provide working code with brief explanations."
},
{
"role": "user",
"content": "What does this JavaScript print to the console?\n```javascript\nconsole.log(1 + '2');\nconsole.log('3' - 1);\nconsole.log(true + true);\nconsole.log... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "Can you research ralph loop proper teqniuqes and implement them here? THe current system is a little buggy\nAssistant action: Bash {\"command\": \"ls /home/user/MythosMini; grep -ril ralph /home/user/MythosMini --include='*' -l | head\", \"description\": \"List repo and find ra... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function to update the statistics of delivered messages in a messaging service. You are provided with a Python dictionary `data` that contains the following keys: 'delivered_basicGet_messages', an integer representing the count of messages del... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "read agents.md"
},
{
"role": "assistant",
"content": "<think>\nThe user’s request is simply “read agents.md”. This implies they want to view the contents of a file named `agents.md`. I need to locate that file in the filesystem. I don’t have any prior knowledge of i... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nptimizer small language model training speedrun modded-nanogpt results 2025\"\n\nLinks: [{\"title\":\"Muon: An optimizer for hidden layers in neural networks | Keller Jordan blog\",\"url\":\"https://kellerjordan.github.io/posts/muon/\"},{\"title\":\"The A... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n2c1b058-c6be-46fa-b830-4dc57cf1e657\" because wake reason is issue_assigned.\n[thinking] <think>\nI have been assigned the issue GLI-240, which is to \"Make agents.\" As the CEO, my role is to lead the company and make strategic decisions, not to do indiv... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "nfrom pathlib import Path\\nsig_lens = []\\nsample = None\\nfor f in (Path.home()/\\\".claude\\\"/\\\"projects\\\").rglob(\\\"*.jsonl\\\"):\\n for line in open(f, errors=\\\"replace\\\"):\\n if '\\\"thinking\\\"' not in line: continue\\n try: rec = json.loads(l... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nws: list[tuple[list[int], int]], device: str, dtype: torch.dtype\\n) -> list[float]:\\n max_len = max(len(tokens) for tokens …[truncated]\nResult: File created successfully at: /home/user/MythosMini/src/mythosmini/benchmarks/scorer.py (file state is cu... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that takes a string as input and returns a modified version of the string based on specific rules. The function should perform the following operations: 1. Convert the input string to lowercase. 2. Replace all occurrences of the le... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with organizing image data for a machine learning project. Implement a function `process_data` that takes in the following parameters: 1. `data_split` (string): Indicates whether the data is for training or testing. It can take the values 'training' or 'testing'.... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a coding agent. When you need to read, write, edit, or run code, emit XML tool calls in this exact format:\n<tool_use name=\"X\" id=\"toolu_01abc\">\n{\"...\": \"...\"}\n</tool_use>\nDo NOT respond with markdown code blocks. Always use <tool_use> XML."
},
{
"r... | 1 | lordx64/fable-tool-use-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a function that generates a welcome message for project coordinators based on their names. The function should accept a coordinator name as input and return a formatted string. If the coordinator name is 'subaru_data', the message should be 'Welcome... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nitle>WATER — FLIP/PIC Incompressible Fluid</title>\\n<style>\\n html, body { margin:0; padding:0; height:100%; overflow:hidden; background:#06080f;\\n font-family: ui-sans-serif, system-ui, \\\"Segoe UI\\\", Roboto, sans-serif; }\\n #c { position:fix... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nude + 1 shared block looped 2-6x with per-loop LoRA + 4 coda, dim 96, RMSNorm/RoPE/SwiGLU, tied embeddings, DSA-style sparse attention (shared model-level lightning indexer, top-128 keys, 64 local window, FlexAttention short path, chunked long path, …[tru... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a network traffic monitoring system that tracks the duration of each session for different source IP addresses. The system should update the end time of a session when a new packet is received from the same source IP address and calculate the to... | 1 | v3-rft-acecode | true |
End of preview. Expand in Data Studio
No dataset card yet
- Downloads last month
- 34