messages list | tier int64 | src string | verified bool |
|---|---|---|---|
[
{
"role": "user",
"content": "You are given a list of detections from a sensor network. Each detection is represented as a tuple containing the arrival time, site ID, time gap from the previous detection at the same site, and the phase of the detection. Your task is to implement a function that takes this l... | 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": "I want you to read agents.md, then follow this experment. THe STM paper is pasted below, use it. I want you to run a 2B model training run on 10% of fineweb-edu \n (python3 train.py 2 100), but use STM on the ordinary version of the model (non SLERP, latest checkpoint) a... | 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 function that validates a list of RPM (Revolutions Per Minute) values. The validation should ensure that each RPM value in the list is a positive integer. If any value is invalid, your function should raise a ValueError with a message indicating w... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Take a look at this project. It needs to be 100% hardened and foolproof. I can't have AI making bad decision and causing a massive failure that ends up costing my company a lot of money because we didn't do our job of title search and approval properly.\nAssistant: I'll take a ... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n:\\n # Render to text, then encode: tokenize=True changed return types across\\n # transformers major versions (list[int] in v4, BatchEncoding in v5).\\n text = tokenizer.apply_chat_template(\\n messages,\\n tools=tools,\\n a... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "there is some weird view snapping issues. THe input bar should only be on the bottom at any time. Every reasoning level tells it to reason more than the last by prompting it in more complex ways.\nAssistant: Two fixes: (1) pin the input bar permanently to the bottom — it curren... | 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": "once claude gets a error about usage exeeded then fallback to opencode, then freebuff. Senario 1: claude runs -> usage limit gone until 8:30 -> opencode runs -> gone until 9:30 -> freebuff runs until 8:30 and the loop continues but its smart and never goes to timed out options.... | 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 grid of size n x m, where n represents the number of rows and m represents the number of columns. Each cell in the grid contains a non-negative integer value. Your task is to find the maximum sum of integers that can be obtained by traversing from the top-left c... | 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": " build_subject_profile,\n10\t name_similarity,\n11\t normalize_apn,\n12\t triangulate_document,\n13\t)\n14\tfrom app.agents.title_extraction import empty_extraction, normalize_extraction\n15\t\n16\t\n17\tdef _wrap(v, c=0.9):\n18\t return {\"value\": v, \"confidenc... | 1 | armand0e/claude-fable-5-claude-code | null |
[
{
"role": "user",
"content": ".npm/_npx/43414d9b790239bb/node_modules/@paperclipai/server/dist;\n 18 Bash:for\n 18 Bash:bunx\n 18 Bash:ps\n 14 Bash:CID=b9ad5795-5f73-496f-9911-83ebb9e9c48a\n 13 Bash:wc\n 13 Bash:CUDA_VISIBLE_DEVICES=\"\"\n 13 Monitor\n 13 Bash:kill\n ... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that attempts to import a specific class from a module. Write a function `import_grief_model` that tries to import the `GPGriefModel` class from the `gp_grief.models` module. If the import is successful, the function should return ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "al seed\\n if [ -n \\\"${SEED:-}\\\" ]; then printf '%s' \\\"$SEED\\\" > \\\"$dir/${SEEDFILE:-seed.txt}\\\"; fi\\n pushd \\\"$dir\\\" >/dev/null\\n local out err rc\\n timeout \\\"$TIMEOUT\\\" $GLINT -p \\\"$prompt\\\" --yolo >stdout.txt 2>stderr.txt\\n rc=$?\\n if grep -... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "Implement a function `stringmethod(s: str) -> str` that modifies a given string `s` based on the following rules: 1. If `s` contains only lowercase letters, return `s` in all uppercase letters. 2. If `s` contains only uppercase letters, return `s` in all lowercase letters. 3. I... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a Python function that processes a list of heads and returns a modified list based on certain conditions. Write a Python function `process_heads(heads, layers)` that takes in the following parameters: - `heads`: A list of integers representing t... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nr.js\", \"content\": \"// WebGL2 fragment-shader ray tracer. No rasterized geometry: every pixel\\n// casts a primary ray against the analytic scene (AABBs + spheres), then\\n// shadow rays, AO rays, and reflection bounces per settings.\\n\\nimport { BOXE... | 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": "…[earlier truncated]…\nstatic\\style.css (file state is current in your context — no need to Read it back)\nAssistant: Now the main application logic:\nAssistant action: Write {\"file_path\": \"C:\\\\Users\\\\aranr\\\\Documents\\\\github\\\\teich\\\\src\\\\teich\\\\studio\\\\st... | 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 complex analysis instructor. Emphasize the rigidity of holomorphic functions — once you know a little, you know a lot."
},
{
"role": "user",
"content": "Explain why complex differentiability is so much stronger than real differentiability. My professor k... | 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": "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 software engineer helping a colleague. Be practical and specific."
},
{
"role": "user",
"content": "What is a health check endpoint?"
},
{
"role": "assistant",
"content": "A health check endpoint is an HTTP endpoint (commonly `/health`... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "Given two lists of numerical values representing the ranks of two variables, implement a function `spearman_rank_correlation` to compute Spearman's rank correlation coefficient. The formula to calculate Spearman's rank correlation coefficient is given by: \\[ \\rho = 1 - \\frac... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nmport shutil\\nimport subprocess\\nimport tempfile\\nimport threading\"}\nResult: The file C:\\Users\\aranr\\Documents\\github\\teich\\src\\teich\\studio\\interactive.py has been updated successfully. (file state is current in your context — no need to Re... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "rt { createEnvironment, CAM_PRESETS } from \\\"./src/scene\\\";\\nimport { applyCine } from \\\"./src/cinematic\\\";\\n\\ndeclare global {\\n interface Window {\\n __ready: boolean;\\n setCam: (name: string) => boolean;\\n listCams: () => string[];\\n playCinematic... | 1 | victor/fable-5-boeing-747-trace | 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": "ect import DeviceInfo, autocast_dtype\n20\tfrom src.mythosmini.model.transformer import MythosMini\n21\tfrom src.mythosmini.telemetry.progress import emit_log_line\n22\tfrom src.mythosmini.telemetry.runlog import RunLog\n23\tfrom src.mythosmini.training.optimizer import build_n... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n\nAssistant action: Bash {\"command\": \"python3 - <<'EOF'\\nPATH='/home/lane/MythosMini/slm_alliance.html'\\nsrc=open(PATH).read()\\n\\nold='''<filter id=\\\"logoBoil\\\" x=\\\"-10%\\\" y=\\\"-10%\\\" width=\\\"120%\\\" height=\\\"120%\\\">\\n <fe... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "My PC keeps crashing! Can you diagnose and patch the bug?\nAssistant: PC crash diagnosis need data. Check logs first."
},
{
"role": "assistant",
"content": "<think>\nThe user reports that their PC keeps crashing and wants a diagnosis and a fix. I need to gather rele... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nks.md and ralph/progress.md. Pick exactly \\\"\\n \\\"one unchecked task (- [ ]) from ralph/tasks.md — the earliest one whose \\\"\\n \\\"prerequisites are met. Complete that one task fully, following all rules \\\"\\n \\\"in AGENTS.m... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that processes version strings according to the Semantic Versioning (SemVer) specification. The version strings consist of three non-negative integers separated by periods (e.g., '1.2.3'). Your function should take a version string... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with processing DNA sequences represented as a list of tuples. Each tuple consists of a sequence identifier (string), a DNA sequence (string), and a string of quality scores (ASCII characters). Your goal is to filter these sequences based on two criteria: the min... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nt OSError:\n164\t break\n165\t if not chunk:\n166\t break\n167\t text = decoder.decode(chunk)\n168\t if text:\n169\t self._broadcast(text)\n170\t tail = decoder.decode(b\... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that simulates a simplified version of a debugger communication system. The function will take in a list of integers representing debugger pipes and a list of strings representing debugger arguments. The function should return a st... | 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]…\nCHAR_TOKENS)}\\nID_TO_CHAR = {v: k for k, v in CHAR_TO_ID.items()}\\nVOCAB_SIZE = 3 + len(CHAR_TOKENS)\\nPROMPT_LEN = 8\\nTHINK_LEN = 7\\nANSWER_LEN = 4\\n\\n\\n@dataclass\\nclass ExperimentConfig:\\n dim: int = 64\\n n_heads: int = 4\\n ffn_hidd... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "Take a look at this project. It needs to be 100% hardened and foolproof. I can't have AI making bad decision and causing a massive failure that ends up costing my company a lot of money because we didn't do our job of title search and approval properly.\nAssistant: I'll take a ... | 1 | Swarm-AI-Research/fable5-traces-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": "You are tasked with implementing a Python function that counts the number of newline characters in a given text string efficiently. The function should read the string in chunks of a specified size and count the number of newline characters to determine the total number of line... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nroughness: 1, emissive: 0x16240a, emissiveIntensity: 0.35\\n });\"}\nResult: The file C:\\Users\\user\\CascadeProjects\\photo-realistic-first-person-survival-game\\index.html has been updated successfully. (file state is current in your context — no need... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\n tests/test_cli.py::test_generate_command_resume_skips_completed_chat_prompts -q 2>&1 | tail -3; git stash pop -q\", \"description\": \"Check if CLI test failure pre-exists on main\", \"timeout\": 120000}\nResult: warning: in the working copy of 'uv.lock'... | 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 string representing a DNA sequence that contains only the characters 'A', 'C', 'G', and 'T'. Write a Python function `process_genetic_sequence(sequence: str) -> dict` that takes the DNA sequence as input and returns a dictionary containing the count of each nucl... | 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 implementing a Python function to parse a given URL and extract its host, file address, and file name. The URL is expected to be in the format `http://<host>/<file_address>/<file_name>`. Your task is to implement the `urlFields` function that takes a URL as ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Given a list of lists of integers and an integer x, your task is to implement a function that returns a list of integers that appear exactly x times across all the lists combined. The order of the elements in the output list should be the same as the order of their first appear... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with creating a Python function that updates a user's profile attributes based on a given user ID and a dictionary of profile attributes. The function should take in the user's ID and a dictionary of profile attributes as inputs. It should return 'True' if the pr... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "Given two integers N and UNROLL, write a Python function `sum_of_multiples(N, UNROLL)` that calculates the sum of all unique multiples of 3 or 5 below the value of N. The UNROLL parameter is intended for optimization but does not need to be utilized in the function's logic. The... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "User: How do I start this?\nAssistant action: Bash {\"command\": \"ls -la /home/lane/rblx\", \"description\": \"List files in project directory\"}\nResult: total 80\ndrwxrwxr-x 6 lane lane 4096 Jun 11 23:08 .\ndrwxr-x--- 159 lane lane 20480 Jun 12 08:36 ..\ndrwxrwxr-x 2 la... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "You are tasked with analyzing a list of order items represented as tuples. Each order item is described by the following tuple structure: (order_num, order_item, prod_id, quantity, item_price). Your goal is to implement a function that takes a list of these tuples and performs ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n:13 node server/index.js\nlane 3982101 0.0 0.0 2812 1892 pts/1 S+ 14:53 0:00 sh -c node server/index.js\nlane 3982102 0.0 0.0 1445828 64100 pts/1 Sl+ 14:53 0:00 node server/index.js\nlane 3982109 0.0 0.0 1515728 54136 pts/... | 1 | v1-glint-terminal | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nMakefile\"}\nResult: 1\tVENV := .venv\n2\tPY := $(VENV)/bin/python\n3\tPIP := $(VENV)/bin/pip\n4\t\n5\t.PHONY: setup test lint fix run\n6\t\n7\tsetup:\n8\t\ttest -d $(VENV) || python3 -m venv $(VENV)\n9\t\t$(PIP) install --quiet --requirement requirements... | 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": "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 file names, write a function that removes the file extensions from each file name and returns a new list containing the modified file names. The file names are represented as strings in the input list. Your function should handle cases where a file name does not... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\nrc.mythosmini.model.transformer import MythosMini\\n\\nm = MythosMini(ModelConfig()).cuda()\\nm.compile(dynamic=True)\\nx = torch.randint(0, 257, (256, 513), device=\\\"cuda\\\")\\ndef step(loops):\\n with torch.autocast(\\\"cuda\\\", dtype=torch.bfloa... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function to calculate the annual bonus for employees based on their performance ratings. The function should take in the employee's salary and performance rating, and return the calculated bonus amount. The bonus is calculated as a percentage ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that processes a list of strings and returns a new list containing only those strings that have a length greater than a specified threshold. Your function should take two parameters: a list of strings and an integer threshold. It shou... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that calculates the total number of unique substrings in a given string. A substring is defined as a contiguous sequence of characters within the string. Your function should take a string as input and return the count of unique subst... | 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 Python function to parse a given URL and extract its host, file address, and file name. The URL is expected to be in the format `http://<host>/<file_address>/<file_name>`. Your task is to implement the `urlFields` function that takes a URL as ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that generates a formatted string representation of an HTTP response. The function should take in the following parameters: a list of addresses, a boolean indicating if the response is fatal, an integer representing the number of retr... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "…[earlier truncated]…\n grep -qE '\\\"status\\\":\\\"(succeeded|failed|cancelled|timed_out)\\\"'; do sleep 5; done\\ncurl -s -m5 \\\"http://localhost:3100/api/heartbeat-runs/$RID\\\" | python3 -c \\\"\\nimport sys,json;r=json.load(sys.stdin)\\nprint('status:',r.get('status'),'|... | 1 | v1-glint-terminal | null |
[
{
"role": "system",
"content": "You are helping an engineer understand Postgres Serializable Snapshot Isolation at the mechanical level. Discuss predicate locks, rw-antidependencies, false positives, and the retry protocol that every SERIALIZABLE client must implement."
},
{
"role": "user",
"con... | 2 | PawanKrd/claude-fable-5-code | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that calculates the total number of unique substrings in a given string. A substring is defined as a contiguous sequence of characters within the string. Your function should take a string as input and return the count of unique subst... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function that processes an error message. Write a function `process_error_message` that takes a string `message` as input and returns a dictionary containing two keys: 'message' which holds the error message string, and 'length' which holds th... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are tasked with implementing a function to calculate the total cost of purchasing mangoes. The price of a single mango is given, and there is a special offer where for every 3 mangoes bought, 1 mango is free. Your task is to write a function `mango(quantity, price)` that ta... | 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": "obabilities are computed using an approximation algorithm from prior work that marginalizes over all possible tokenizations. The byte-level head is removed after distillation, leaving a standard token-level model.\n\n## Computational Requirements\n\n**Single GPU feasibility**: ... | 1 | 1EYE4ALL/Fable-5-traces | null |
[
{
"role": "system",
"content": "You are a knowledgeable technology educator. Explain concepts at the right level for the question."
},
{
"role": "user",
"content": "What is the difference between a library and a framework?"
},
{
"role": "assistant",
"content": "# Library vs. Framewor... | 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": "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": "[Request interrupted by user]\nin agents.md tell agents to ignore mypy and use pyaot.py and to fix any bugs in the script if needed, but follow its advice. Also, you dont need to run a verificati0on run if the change is tiny and doesnt affect training.\nAssistant action: Bash {... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "…[earlier truncated]…\nSSISTANT (tool call) TaskCreate input={\"subject\": \"Build 1M-param model per plan.md\", \"description\": \"Byte-level vocab, prelude/shared-looped/coda blocks, per-loop LoRA, RMSNorm+RoPE+SwiGLU, tied embeddings, ~1M params. Tests prove param count, for... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a voting system for a competition. The voting system follows a simple elimination process where candidates compete in rounds, and the winner of each round advances until a majority winner is determined. You are given a function `determine_winner... | 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": "[Request interrupted by user for tool use]\nMake the ralph loop smarter. It should do this. make goals for prompt -> tell agent to execute first one -> verify it did it!!! -> if not, prompt anoter agent to continue where it left off -> ect.... also, ensure that the agent is tol... | 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": "Build out a prototype for this potential system for stock AI analysis, a self evolving algorithim generating system where the model can make an algorithm, backtest on some stock data, then use the results to try and improve the algorithm. It should be able to learn from its fai... | 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": "…[earlier truncated]…\nen updated successfully. (file state is current in your context — no need to Read it back)\nAssistant action: Edit {\"replace_all\": false, \"file_path\": \"/home/user/GR/glint-cli/src/tui.tsx\", \"old_string\": \" const cfg = loadConfig();\\n const tho... | 1 | Swarm-AI-Research/fable5-traces-sft | null |
[
{
"role": "user",
"content": "You are tasked with implementing a function that processes a list of 28x28 pixel grayscale images represented as 2D arrays and predicts the handwritten digit (0-9) for each image using a simple model. Your function should take a list of 2D arrays `images` and return a list of p... | 1 | v3-rft-acecode | true |
[
{
"role": "system",
"content": "You are a linear algebra teacher in the Strang tradition: lead with the four fundamental subspaces picture and let rank-nullity fall out as the obvious consequence."
},
{
"role": "user",
"content": "Compare the column space, null space, row space, and left null sp... | 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": "You are tasked with creating a Python function that processes a given dictionary. The function should take a dictionary as input, which is guaranteed to contain a key 'message'. Your task is to implement the function `process_message` that performs the following operations: 1. ... | 1 | v3-rft-acecode | true |
[
{
"role": "user",
"content": "You are given a list of integers representing the heights of buildings in a city. Your task is to determine the number of buildings that can see the sunset. A building can see the sunset if there are no taller buildings to its right. Write a function `countBuildings(heights: Li... | 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 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.