messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"role": "user",
"content": "You are tasked with implementing a function that generates a unique slug for a given category name. A slug is a URL-friendly version of a string, typically used in web applications to represent a resource. The function should take a category name as input and return a unique sl... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "no em-dashes\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/user/MythosMini/slm_alliance.html\", \"old_string\": \"<p><strong>This is where Glint Research has been.</strong> This project — built in part by Glint Research — is what we've been... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function to switch predictions based on confidence levels. Given a list of true labels `y_list`, a list of predicted labels `predictions`, and a list of confidence scores `confidences`, your goal is to implement a function `switch_predictions`... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n\\\"fb2\\\"></span><span class=\\\"fb3\\\"></span></div>\"}\nResult: The file /home/user/rblx/public/js/app.js has been updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Edit {\"replace_all\": false... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function `manage_server` that simulates server management operations without a database. Your function should take the following parameters: \n- `group_id`: an integer representing the ID of the group to which the server belongs (0 indicates n... | 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 serializer for a simple Tweet model in a Python application. The Tweet model has three fields: author, content, and likes, and you are required to implement a function that accepts a dictionary representation of a Tweet and returns a serialized ve... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nate } from \\\"react\\\";\\nimport { Box, Static, Text, render, useApp, useInput, useStdin } from \\\"ink\\\";\\nimport { COMMANDS, resolveCommand, runCommand } from \\\"./commands.ts\\\";\\nimport { type AgentState, newAgentState, runTurn } from \\\"./co... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with writing a function that extracts and returns a list of operations performed on a quantum circuit from a given code snippet. The code snippet consists of operations represented as lines of code. Each operation could be modifying the position of a handler, add... | 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": "You are tasked with creating a Python function that transliterates a given input string into a different script. Write a function called `transliterate` that takes a single string as input and returns the transliterated version of that string. For the purpose of this problem, l... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nwrap\\\">\\n <div class=\\\"auth-logo\\\">\", \"new_string\": \" <div class=\\\"auth-wrap\\\">\\n <div class=\\\"auth-bg\\\"><span class=\\\"b1\\\"></span><span class=\\\"b2\\\"></span><span class=\\\"b3\\\"></span></div>\\n <div class=\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nat-header\\\">\\n <span class=\\\"channel-hash\\\">#</span>\", \"new_string\": \" <header class=\\\"chat-header\\\">\\n <button class=\\\"sidebar-toggle\\\" id=\\\"sidebar-toggle\\\" aria-label=\\\"Togg... | 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": "ge[], opts: ChatOptions): Promise<ChatResult> {\nAssistant action: Bash {\"command\": \"grep -n \\\"MODEL\\\\|apiKey\\\\|API_KEY\\\" src/core/config.ts | head; echo ===; KEY=$(grep -o '\\\"gsk_[^\\\"]*\\\"' src/core/config.ts | tr -d '\\\"'); [ -n \\\"$GROQ_API_KEY\\\" ] && KEY... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n, config, dtype)\", \"new_string\": \" for epoch in range(1, config.epochs + 1):\\n order = torch.randperm(active.shape[0], generator=generator).to(pool.device)\\n shuffled = active[order]\\n losses, settled_micro = stm_epoch(model... | 1 | Swarm-AI-Research/fable5-traces-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": "As a curious learner trying to understand, i'm a team lead here, for a personal learning goal. I'm lazy and looking for best practices about why SSA form enables sparse conditional constant propagation — the actual mechanism beyond just 'def-use chains'. Is it the phi nodes or ... | 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": "user",
"content": "okay, you can stop caveman to explain\nAssistant: Sure — here's the full explanation in plain prose.\n\n## How this architecture differs from a standard Llama\n\nA normal Llama is a straight stack of N distinct transformer layers — every layer has its own weights, and a token p... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with processing training data for a machine learning model. Implement a function `process_training_data(features, targets, i_train)` that takes three parameters: \n- `features`: a list of lists, where each inner list represents the features for a data point. \n- ... | 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": "html\"}\nResult: 1\t<!doctype html>\n2\t<html lang=\"en\">\n3\t<head>\n4\t<meta charset=\"utf-8\" />\n5\t<meta name=\"viewport\" content=\"width=device-width, initial-scale=1\" />\n6\t<title>Drop Anywhere SVG Stroke Logo Intro</title>\n7\t<style>\n8\t html,body{margin:0;min-he... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates a simplified version of a job submission system. Each job has a unique identifier, a priority level, and a time estimate for completion. Your function should accept a list of job submissions, each represented by a tuple... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a program that validates a list of input arguments. Your function should check if the number of input arguments is exactly 5. If the number of input arguments is not 5, the function should raise a ValueError with the message 'Incorrect number of arg... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nk, then change this checkbox from [ ] to [x]. Do nothing else and do not commit.\\\\n' > ralph/tasks.md; printf '# Ralph progress: probe\\\\n' > ralph/progress.md; echo ready\", \"description\": \"Reset freebuff lock and write probe task\"}\nResult: ready... | 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": "8 371.886 471.573 349.21 458.143C343.837 463.724 338.205 469.115 332.5 474.357C304.301 500.266 278.411 530.489 249.654 555.633C248.519 565.856 249.552 584.308 249.75 595.155C249.963 613.433 250.047 631.713 250 649.992L250.903 764.121C251.036 799.829 250.514 836.308 251.515 871.... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\niceInfo,\\n autocast_dtype,\\n describe_device,\\n detect_device,\\n)\\nfr …[truncated]\nResult: File created successfully at: /home/user/MythosMini/train.py (file state is current in your context — no need to Read it back)\nAssistant action: Edi... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "I'm a game developer and I'm working for an open source contribution. I'm paranoid about edge cases about how to find and fix a memory leak in a C++ binary processing large files in a TypeScript Django app with Cassandra. How do you reason through this? I'm especially wondering... | 2 | armand0e/Fable-5-Chat | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nit input={\"replace_all\": false, \"file_path\": \"/home/lane/log/logo.html\", \"old_string\": \" filter:drop-shadow(0 10px 24px rgba(0,0,0,.12));\\n animation:aiLogoCameraIn202606 1.15s cubic-bezier(.2,.8,.18,1) both;\\n }\", \"new_string\":... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with developing a function that simulates the basic functionality of image segmentation without the use of external libraries. Your function should take a 2D list (matrix) of integers, representing pixel values of an image, and return a new 2D list where each seg... | 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 probabilist explaining stochastic calculus to a strong student. Emphasize why the rules differ from ordinary calculus, and ground formulas in what Brownian motion actually does."
},
{
"role": "user",
"content": "Derive Ito's formula for f(B_t) from scrat... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that finds the index of a stone used in a potion from a predefined list of stones. The function takes in two parameters: `stone_inst` and `stone`. You need to return the index of the `stone` in the list of stones if `stone_inst` is pr... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "User: When the model is training, it says something like 750M/1.00G Can you explain what both of these mean?\nAssistant action: Bash {\"command\": \"grep -rn \\\"1.00G\\\\|/1\\\\.\\\\|tokens_seen\\\\|progress\\\" /home/lane/MythosMini --include=*.py -l | head; grep -rn \\\"G\\\... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nOOL RESULT: (Bash completed with no output)\nAssistant action: Bash {\"command\": \"cat /home/lane/.paperclip/adapter-plugins/groq-paperclip-adapter-r8/package.json; wc -l /home/lane/.paperclip/adapter-plugins/groq-paperclip-adapter-r8/dist/server/*.js\",... | 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": "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 of ranges, where each range is represented as a tuple containing two integers that define the start and end of the range (inclusive). Your task is to implement a function that returns a sorted list of all unique integers that fall within the specified range... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with calculating the denominator of a fraction based on the given inputs related to a linear programming problem. Implement a function `calculate_denominator(A, c, dual, b)` that calculates the denominator using the following parameters:\n\n- `A`: A 2D list of li... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nvarying vec3 vWorld;\\n void main() {\\n vec3 baseCol = mix(vec3(0.16, 0.25, 0.07), vec3(0.42, 0.56, 0.19), vUv.y);\\n baseCol *= 0.8 + vTint * 0.4;\\n …[truncated]\nResult: The file C:\\Users\\user\\CascadeProjects\\photo-realistic-fi... | 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]…\n <Markdown text={stream} />\\n </Box>\\n </Box>\\n ) : null}\\n\\n {running && thoughtsOn && thoughtLines.length > 0 && (\", \"new_string\": \" </Static>\\n\\n <Box flexDirection=\\\"column\\\" height={dynRows}>\\n ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Given a string representing the lyrics of a song, your task is to implement the function `extract_lyrics` that takes this string as input and returns only the lyrics without any leading or trailing whitespace. If the input string is empty or contains only whitespace, the functi... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that processes financial data to identify the adjusted high and low markers for a 52-week period. The function `calculate_52_week_hl_marker` takes in four parameters: `open_price`, `high_price`, `low_price`, and `close_price`, along w... | 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": "Hey there! Please read agents.md, read all files it wants you to, and follow it word for word. TASK: Build a basic training script for a 1M paramater model, it should be hyper effecent, with paramaters. HOW: read plan.md. DATASET: fineweb-edu with quality limit, only do above 4... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function to calculate the total number of valid triangles that can be formed from a given list of positive integers. A valid triangle is formed by selecting three integers from the list such that the sum of any two integers is greater than the... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": " if (phase !== \"ready\") return;\n191\t push({ kind: \"banner\", text: \"\" });\n192\t trace(\"session.start\", { mode: \"tui\" });\n193\t if (opts.resume) {\n194\t const loaded = loadSession(opts.resume);\n195\t if (loaded) {\n196\t stateRef.curren... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a concise coding assistant. Provide working code with brief explanations."
},
{
"role": "user",
"content": "Walk me through implementing a basic web scraper that handles pagination, rate limiting, and errors."
},
{
"role": "assistant",
"content... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "idden; background: #000; }\\n body { font-family: \\\"Segoe UI\\\", Roboto, sans-serif; user-select: none; }\\n #app { position: fixed; inset: 0; }\\n canvas { display: block; }\\n\\n /* ---------- HUD ---------- */\\n #hud { position: fixed; inset: 0; pointer-ev... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that performs text processing for a natural language processing (NLP) project. The function should include the following functionalities: extracting words from a given string, creating a unique vocabulary from a list of words, and nor... | 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": "This is what happens when I load it from hf. [Image #1]\n[Image: source: /home/user/.claude/image-cache/bd2f5aa9-a725-436b-b4ef-c1e05496c7cb/1.png]\nAssistant: CSS/JS are stale-cached — HTML is new but browser/HF proxy serves old `style.css` + `app.js`, so no class matches, no ... | 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": "As a professor designing exam questions with solutions, i'm a principal architect here. I'm for a conference talk and overwhelmed by complexity about design a zero-downtime database migration for adding a non-nullable enum. We're on Go/FastAPI with MongoDB. What would you consi... | 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": "…[earlier truncated]…\nst content = firstBrace !== -1 && lastBrace >= firstBrace\n113\t ? raw.substring(firstBrace, lastBrace + 1)\n114\t : raw;\n115\t let parsed;\n116\t try {\n117\t parsed = JSON.parse(content.trim());\n118\t ... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>\n<command-name>/login</command-n... | 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 provided with a dataset sample from a Bayesian Network in **`/app/data/bn_train.tsv`**. The file is **tab-separated** (TSV), not comma-separated. The column names are the same as in the original task (`U`, `R`, `Y`, `M`, `D`).\nYour first task is to recover the underlyi... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that checks if any team has reached their submission rate limit for a specific task in a coding challenge platform. A team can only submit a solution every 15 minutes. Given a list of submission timestamps for each team and the curren... | 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": "User: Please fix paperclip AI with all the bugs you find in these things I expected to be completed. http://127.0.0.1:3100/GLI/issues/GLI-260 http://127.0.0.1:3100/GLI/issues/GLI-263 http://127.0.0.1:3100/GLI/issues/GLI-258\nAssistant action: Skill {\"skill\": \"paperclip\", \... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "sed time\\npid=$(pgrep -f recot_truncated.py | head -1)\\necho \\\"pid=$pid elapsed=$(ps -o etimes= -p $pid 2>/dev/null)s\\\"\\necho \\\"completed(sidecar)=$(wc -l < recot_full.jsonl)\\\"\\necho \\\"errors=$(grep -c '^ERR' recot_progress.log)\\\"\", \"description\": \"Process e... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates a simple banking transaction system. The function should take a list of tuples, where each tuple represents a transaction. Each transaction can either be a deposit or a withdrawal. A deposit is represented by a tuple wi... | 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]…\n:test_config_endpoints\r\ntests/test_studio.py::test_prompts_endpoints\r\ntests/test_studio.py::test_trace_listing_and_preview\r\ntests/test_studio.py::test_index_served\r\ntests/test_studio.py::test_session_endpoints_validation\r\n C:\\Users\\user\\Docu... | 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]…\n w;\\n c.height = h;\\n }\\n }\\\"\\\"\\\"\\nnew = \\\"\\\"\\\" resize(scale) {\\n const c = this.canvas;\\n let w = Math.max(2, Math.round(c.clientWidth * scale));\\n let h = Math.max(2, Math.round(c.clientHeight * scale));\\n // ha... | 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]…\nmport Tensor\n6\t\n7\tfrom src.mythosmini.benchmarks.runner import BenchmarkScores\n8\tfrom src.mythosmini.config import SLERP_MAX_GENERATIONS, SLERP_T_SWEEP, SLERP_TOP_K\n9\tfrom src.mythosmini.merging.slerp import slerp_state_dicts\n10\t\n11\tSTALL_GENE... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a custom error handling mechanism for a web application that processes SQL queries. Your goal is to create a custom exception class called `InvalidSQLError` that inherits from the base `Exception` class. This exception should be raised when a no... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nr(a, b, 0.0), a, atol=1e-5)\\n\\n\\ndef test_slerp_tensor_midpoint_lies_between_on_sphere() -> None:\\n a = torch.tensor([1.0, 0.0])\\n b = torch.tensor([0.0, 1.0])\\n mid = slerp_tensor(a, b, 0.5)\\n expected = math.sin(math.pi / 4) / math.si... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are given a list of integers representing the responses of customers to a marketing campaign, where 1 indicates a positive response and 0 indicates a negative response. Your task is to implement a function that calculates and returns the accuracy, precision, recall, and F1 ... | 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 processing book titles from a list. Write a function called `process_titles` that takes a list of book titles as input and returns a new list where each title is transformed to uppercase. Your function should handle the case where the input list is empty by ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Make me a photorealistic survival game. We are in the woods surrounded by trees, hills, grass, flowers, nature. The lighting should look really real as well. We can walk around, the wind is blowing, there's ambient sounds and everything, as close to photo-realism as possible\nA... | 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 implementing a function to process a list of software versions and their licenses. The function should take a list of dictionaries, where each dictionary represents a software version and its corresponding license. The goal is to transform the license data f... | 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": "As a pragmatic developer shipping code, i'm theoretical and academic for a mentorship session and need to add a non-nullable enum to a 2M-row PostgreSQL table with zero downtime. I'm a graduate student using psql and migration scripts. How do you handle how to verify data integ... | 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": "You are tasked with implementing a function that processes a given hotkey string to create a layout configuration. The hotkey string consists of a sequence of mode-button pairs, where each mode is followed by a button. The function should validate the hotkey and create a layout... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that simulates a simplified training loop for a machine learning model. The function should take in a list of loss values for each epoch and return the average loss for every 5 epochs. Additionally, if the epoch number is a multiple o... | 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 implementing a function that represents a simple key-value store. This function should allow you to add key-value pairs and retrieve the value associated with a given key. If the key does not exist, the function should return None. Additionally, you should b... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that checks if any team has reached their submission rate limit for a specific task in a coding challenge platform. A team can only submit a solution every 15 minutes. Given a list of submission timestamps for each team and the curren... | 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 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.