messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"role": "user",
"content": "[Request interrupted by user for tool use]\nITS CLIMBING. IT SHOULD BE DEAD. [Image #1]\n[Image: source: /home/user/.claude/image-cache/602033e7-dc55-4b7f-909f-1c67135d8f4b/1.png]\nAssistant action: Bash {\"command\": \"ps aux --sort=-%mem | head -12; free -h | head -2\", \"des... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\ns/rules/process.md, configuration section) and the first docs/functions.md entries.\n\n## [2026-06-09 17:18] — scaffolding verification\n\n**TL;DR:** All Makefile targets verified. `make lint` initially failed on formatting; fixed with `make fix`; everyth... | 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": "Make it use https://huggingface.co/google/diffusiongemma-26B-A4B-it\nAssistant: Look at bot.py image gen code first.\nAssistant action: Bash {\"command\": \"grep -n -i \\\"huggingface\\\\|hf.co\\\\|image\\\\|diffus\\\\|gemma\\\\|model\\\" /home/user/Blindbot/bot.py | head -60\"... | 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 utility that manipulates time data given a start time and an optional stop time. Your function should accept two parameters: a start time and an optional stop time, both in the format 'HH:MM:SS' (hours, minutes, seconds). The function should retur... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "remove the dots.\nAssistant: Dots = round line caps rendering as points before each segment grows. Switch caps to butt:\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/user/log/logo.html\", \"old_string\": \" stroke-linecap:round!important;\", \"new... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nchema,\n/home/lane/paperclip/packages/shared/src/index.ts:924: createAgentSchema,\n/home/lane/paperclip/packages/shared/src/adapter-types.test.ts:2:import { AGENT_ROLE_LABELS, acceptInviteSchema, createAgentSchema, updateAgentSchema } from \"./index.js\"... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that takes a list of user dictionaries and returns a list of user emails that match a given search term. Each user dictionary contains the keys 'nome', 'email', and 'senha'. The function should filter the users by checking if the sear... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "e)\\nprint(\\\"path\\\",p)\\nprint(sorted(os.path.basename(x) for x in glob.glob(p+\\\"/*\\\")))\\nfrom transformers import AutoTokenizer\\nt=AutoTokenizer.from_pretrained(p)\\nmsgs=[{\\\"role\\\":\\\"user\\\",\\\"content\\\":\\\"hi\\\"},{\\\"role\\\":\\\"assistant\\\",\\\"cont... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nNEON<span>STRIKE</span></h1>\\n <p class=\\\"tagline\\\">fully ray-traced arena FPS · every pixel is a ray</p>\\n <div class=\\\"map-pick\\\" id=\\\"map-pick\\\"></div>\\n <button id=\\\"btn-play\\\" class=\\\"btn-primary big\\\" …[truncated]\nRe... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "For a conference talk, I'm dealing with family group chat sharing vaccine studies from unknown journals. I'm a junior developer who wants the checklist for evaluating whether a study is worth taking seriously. What worries me is what epistemological red flags mean 'this is misi... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "You are tasked with implementing a data splitting algorithm for a dataset used in machine learning. Write a function `split_data` that takes the following parameters: \n- `data`: A list of tuples, where each tuple represents a data point and its corresponding label. \n- `train_... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that validates client information. The function should take a dictionary as input and check if it contains the required keys: 'name' and 'email'. If both keys are present, the function should return 'Client added successfully'. If eit... | 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": "user",
"content": "…[earlier truncated]…\n overall_score,\\n wiki_score,\\n)\\n\\nFIXTURE = Path(__file__).parent / \\\"fixtures\\\" / \\\"leaderboard_index.html\\\"\\n\\n\\ndef load_entries() -> list[LeaderboardEntry]:\\n return parse_leaderboard_html(FIXTURE.read_text(encoding=\\\"utf-8\... | 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": "You are tasked with checking for duplicate enum items in a given dictionary that represents enum definitions. The input is a dictionary 'enumdata' where the keys are enum names and the values are sets of strings representing the enum items. Your goal is to implement a function ... | 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": "…[earlier truncated]…\nSISTANT (message): Removed one wrapper level — must drop the orphaned closing tag at the end:\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/lane/GR/glint-cli/src/tui.tsx\", \"old_string\": \" </Box>\\n </Box>\\n </Box>... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that processes command-line arguments for running package tests. Specifically, the function should take a list of command-line arguments and parse them to determine if the option for outputting results in XML format is specified. The ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "I'm paranoid about edge cases for a side project and trying to understand regular expressions and their equivalence to finite automata. I'm a CS student struggling with why backreferences make regexes non-regular. How do you prioritize what to check first? The part I can't reso... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "You are tasked with creating a simple banking system that manages a bank account. Write a function `manage_bank_account` that takes an account number, an initial balance, a list of transactions, and returns the final balance of the account. The transactions can include either d... | 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": "…[earlier truncated]…\ntitle>Drop Anywhere SVG Stroke Logo Intro</title>\n7\t<style>\n8\t html,body{margin:0;min-height:100%;background:#18181b;display:grid;place-items:center;font-family:system-ui,sans-serif;}\n9\t</style>\n10\t</head>\n11\t<body>\n12\t\n13\t<!-- COPY FROM HE... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "mini/model/transformer.py\", \"description\": \"Read transformer model\"}\nResult: from typing import cast\n\nimport torch\nfrom torch import Tensor, nn\nfrom torch.nn import functional\n\nfrom src.mythosmini.config import ModelConfig\n\n\ndef build_rope_cache(config: ModelConf... | 1 | 1EYE4ALL/Fable-5-traces | 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]…\nde carrying the part data\\n let o = h.object;\\n while (o && !o.userData.part) o = o.parent;\\n if (o && o.userData.part) return o.userData.part;\\n }\\n return null;\\n }\"}\nResult: The file /home/user/rblx/public/js/studio/studio... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n test state/replan/parity changes\", \"timeout\": 180000}\nResult: .venv/bin/ruff format --check src/ tests/ ralph.py\n6 files already formatted\n.venv/bin/ruff check src/ tests/ ralph.py\nAll checks passed!\n.venv/bin/python -m mypy --strict src/ tests/ ... | 1 | v1-glint-terminal | 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 implementing a Python function that simulates a simplified command execution system. The function should take in a command and a list of arguments, then execute the command with the provided arguments. The function should handle any potential exceptions and ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that manages a list of hooks for monitoring and profiling code execution. Each hook is represented by a callable function that takes no parameters and returns a string when executed. Your task is to implement a function `manage_hooks(... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Given an unsigned integer n, write a function `reverseBits` that returns the integer value of n with its binary representation reversed. The function should iterate through the bits of the input integer n and construct the reversed binary representation. The input integer n wil... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n 1 && tmux capture-pane -t glint -p | tail -32\", \"description\": \"Test /help command in TUI\"}\nResult: ✦ glint v1.0.0 · Glint Research · a tiny agent that punches above its weight\n groq/compound · session e7f339df · /tmp/glint-test\n /help for comm... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You need to implement a function that compares two cross-validation scores: `score_10cv` and `score_90lccv`. The comparison is based on a predefined threshold `r` and a tolerance value `tol`. If `score_90lccv` is NaN (not a number), the function should return True if `score_10c... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "As a patient tutor explaining from first principles, i'm curious and exploratory for a side project because considering intermittent fasting for health reasons. I'm a mobile developer trying to figure out what the actual research says about metabolic effects. Where's the line w... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "[Request interrupted by user for tool use]\nit caught it\nAssistant: Good. Finishing per rules: lint/test, update docs, journal, commit.\nAssistant action: Bash {\"command\": \"make lint > /tmp/lint.out 2>&1 && make test > /tmp/test.out 2>&1; echo \\\"lint=$?\\\"; tail -1 /tmp/... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nsMini/src/mythosmini/benchmarks/runner.py has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Bash {\"command\": \".venv/bin/ruff check --fix src/mythosmini/benchmarks/runner.py && .venv/bin/... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "create the most realistic and accurate 3D model of the taj majal (with surrounding scenery). build a camera system to allow free view inspection of the model.\n\nPut it all together in the end with a 20 second showcase in a very impressive way. You will be the director of that ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "[Request interrupted by user for tool use]\nBugs: gun is now pointed to the left. it needs to be as if I was holding it out infront of me. the bottom at my hand. the tip looking at where it would land if I shot rn. I dont like the random sparkle effects. Also everything is way ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a Python function that performs polynomial operations. The function should take two polynomials as input and return the result of adding and multiplying these polynomials. Each polynomial is represented as a list of coefficients, where the index... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nort datetime, timezone\\nfrom pathlib import Path\\nfrom typing import Any\\n\\nfrom ..config import Config, PromptInput\\nfrom ..runner import (\\n TEICH_PROMPT_FILE_NAME,\\n ChatRunner,\\n ClaudeCodeRunner,\\n CodexRunner,\\n HermesRunner... | 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": "You are given a list `l` containing integer elements and a list `n` containing string elements. Your task is to implement a function `process_lists(l: List[int], n: List[str]) -> Tuple[List[int], str, str]` that performs the following operations:\n1. Returns the reverse of the ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a 2D array representing a game board. Each cell in the array contains an integer representing the score of that cell. Your task is to implement a function `max_score(board)` that finds the maximum score that can be obtained by moving from the top-left cell to the ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function to simulate a custom data loader for a machine learning model. The function should take a list of input features and corresponding labels, and return batches of data. Your task is to implement a function named `custom_data_loader` that me... | 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": "user",
"content": "Continue from where you left off.\nAssistant: No response requested.\nSorry to interrupt you but I went ahead and just did my own testing. The interactive chat looks cool, but I was hoping it would give the native claude code, hermes, codex, pi terminal view. as if I had just g... | 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": "…[earlier truncated]…\nent_prompt={len(p)} teacher_prompt={len(tp)} target={len(tgt)}\\\")\\n\\nex = json.loads(lines[0])\\np, tgt = expert_target_ids(tok, ex[\\\"context\\\"], ex[\\\"expert\\\"], tools, kw)\\nprint(\\\"--- target decoded ( …[truncated]\nResult: \u001b[31;1mC:\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates sending GET and POST requests to a specified URL and returning the appropriate response. The function should take three parameters: a string 'url' representing the target URL, a string 'method' which can either be 'GET'... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given an array `prices` where `prices[i]` is the price of a given stock on the `i`-th day, and a non-negative integer `fee` representing a transaction fee. You want to maximize your profit by making as many transactions as you want, but you must pay the transaction fee ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that counts the occurrences of each word in a given string. The function should ignore case sensitivity and punctuation, and only consider alphanumeric characters as part of a word. Additionally, the function should exclude common ... | 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]…\n}\\n\\nexport interface ChatResult {\\n content: string;\\n reasoning?: string;\\n usage: Usage;\\n breakdown?: BreakdownEntry[];\\n model: string;\\n}\\n\\nexport type DeltaChannel = \\\"content\\\" | \\\"reasoning\\\";\\n\\nexport interface ChatOpt... | 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": "You are tasked with creating a Python function that takes a list of station names and their corresponding URLs, and returns a dictionary where the keys are the station names and the values are the URLs. The function should have the following signature: `def build_station_dict(s... | 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 backend engineer who has spent years building idempotent APIs and orchestrating long-running workflows across payment, inventory, and notification systems. You can talk concretely about idempotency keys, deduplication windows, exactly-once illusions, and where these... | 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": "…[earlier truncated]…\n\t <link href=\"https://fonts.googleapis.com/css2?family=Fira+Code:wght@400;500&family=Inter:wght@300;400;500;600;700;800&display=swap\" rel=\"stylesheet\">\n10\t <link rel=\"stylesheet\" href=\"style.css?v=2\">\n11\t</head>\n12\t<body>\n13\t <!-... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "ification arrives.\nAssistant: Status while CoT generation finishes:\n\n- **Task 1 done** — 105 Fable 5 user→reply pairs extracted (real thinking was encrypted/empty, confirming CoT must be synthesized)\n- **Task 2 running** — 83/105 CoT generated via qwen3.5:4b, verified good ... | 1 | 1EYE4ALL/Fable-5-traces | 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 to manage different types of commands for a gaming assistant bot. The function should allow for executing commands based on their names and additional arguments. You are given a predefined list of command modules, each represented ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a program that can parse and extract information from a Django migration file. The input content of the migration file will be in the format: `# Generated by Django {version} on {date_time}`, where `{version}` is a version number (e.g., '1.11') and ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "As a pragmatic developer shipping code, for a conference talk, I need to produce a 5,000-word essay on the future of programming. I'm a self-taught programmer who's methodical and careful about the end of programming as we know it. It must include: shift from writing code to sp... | 2 | armand0e/Fable-5-Chat | 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": "how much more effecent is it than normal on infer tasks? (random 1000 questions, give %)\nAssistant: Measuring directly: 1000 random unseen questions, trained models, baseline AR vs double-decoder inference wall-time.\nAssistant action: Bash {\"command\": \"CUDA_VISIBLE_DEVICES... | 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 Python function that compares the contents of two lists of filenames and ensures that they are identical, except for specific filenames that should be ignored. Your function should take in two lists of filenames and a list of filenames to ignore. ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with simulating a simple multi-agent reinforcement learning environment. Each agent has a policy represented by a list of weights for its actions. Implement a function `update_policy(weights: List[float], actions: List[int], advantages: List[float]) -> List[float... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "As a debugger helping trace through complex logic, i'm lazy and looking for best practices for an interview prep where I need to review a partner's REST API design for REST semantics and security. I'm a graduate student using Scala and Axum. How do you form a hypothesis here? H... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "You are tasked with calculating the entropy of a given list of integers, which serves as a measure of randomness or unpredictability in the dataset. Implement a function `calculate_entropy(data)` that takes a list of integers `data` as input and returns the entropy value based ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a function that counts the number of unique characters in a given string. Your function should ignore spaces and be case insensitive. Implement the function `count_unique_characters(s: str) -> int` that takes a string `s` as input and returns the nu... | 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 given a 2D grid representing a maze, where 0s represent open paths and 1s represent obstacles. Your task is to implement a function that finds the shortest path from a starting position to an ending position. You can only move vertically or horizontally (no diagonal mov... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "The core idea:\n- Bitnet = ternary {−1,0,1} in a 2-bit container (1.58-bit effective)\n- Dragonoid: \"Why not do the same for 4-bit, since it's all about sparsity anyway?\"\n- Clock = sparse 3.5-bit format: 12 states (like clock hours → hence the name)\n- First version: 12 stat... | 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": "do it all, but dont heavily shrink the file\nAssistant: Check repo contents first.\nAssistant action: Bash {\"command\": \"ls -la /home/user/MythosMini && find /home/user/MythosMini -name \\\"*.py\\\" | head -20 && cat /home/user/MythosMini/README.md 2>/dev/null | head -30\", \... | 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 senior application security engineer. Explain CSRF defenses for modern SPA+cookie architectures with precise attention to browser behavior, subdomain pitfalls, and which combinations of defenses actually work."
},
{
"role": "user",
"content": "I've read ... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nssert results[\\\"thinker_final_loss\\\"] < 1.0\\n assert results[\\\"talker_final_loss\\\"] < 1.0\", \"new_string\": \" assert results[\\\"thinker_final_loss\\\"] < 1.5\\n assert results[\\\"talker_final_loss\\\"] < 1.5\"}\nResult: The file /hom... | 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": "You are given two lists of equal length, `mzs` and `fwhms`, representing the mass-to-charge ratios and the full width at half maximum values, respectively. Your task is to write a Python function `extract_real_peaks(mzs, fwhms, threshold)` that processes these two lists and ret... | 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": "…[earlier truncated]…\nsMini/tests/test_ralph_helpers.py <<'EOF'\\n\\n\\ndef test_unfinished_work_remains_true_when_tasks_file_missing(\\n tmp_path: Path, monkeypatch: pytest.MonkeyPatch\\n) -> None:\\n monkeypatch.setattr(ralph, \\\"TASKS_FILE\\\", tmp_path / \\\"tasks.m... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a `RestraintManager` that manages restraints in a molecular modeling application. The manager should have the capability to add and delete restraints from a GUI list. Write a function `manage_restraints` that takes the following parameters: a li... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\ncated]\nAssistant action: Bash {\"command\": \"timeout 900 .venv/bin/python - <<'EOF'\\nimport time, random, torch\\nfrom src.mythosmini.config import ModelConfig\\nfrom src.mythosmini.model.transformer import MythosMini\\n\\nfor fp4 in (True, False):\\n ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list of integers representing the scores of a game. The game has a rule that a player's score is computed based on the scores of the last two turns. If the last two turns have the same score, the player's score is doubled. Otherwise, the player's score is the su... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a senior software engineer helping a colleague. Be practical and specific."
},
{
"role": "user",
"content": "What is linting?"
},
{
"role": "assistant",
"content": "# Linting\n\n**Linting** is the automated process of analyzing source code to f... | 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 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.