messages listlengths 15 246 |
|---|
[
{
"role": "system",
"content": "You are an autonomous coding agent running on the user's machine.\n\nYou work in the current directory of a real repository. Use your tools to read, search, create, and edit files and to run shell commands (tests, builds, type-checkers). Some tools are deferred: only their na... |
[{"role":"system","content":"You are an autonomous coding agent running on the user's machine.\n\nYo(...TRUNCATED) |
[{"role":"system","content":"You are an autonomous coding agent running on the user's machine.\n\nYo(...TRUNCATED) |
[{"role":"system","content":"You are an autonomous coding agent running on the user's machine.\n\nYo(...TRUNCATED) |
[{"role":"system","content":"You are an autonomous coding agent running on the user's machine.\n\nYo(...TRUNCATED) |
[{"role":"system","content":"You are an autonomous coding agent running on the user's machine.\n\nYo(...TRUNCATED) |
[{"role":"system","content":"You are an autonomous coding agent running on the user's machine.\n\nYo(...TRUNCATED) |
[{"role":"system","content":"You are an autonomous coding agent running on the user's machine.\n\nYo(...TRUNCATED) |
[{"role":"system","content":"You are an autonomous coding agent running on the user's machine.\n\nYo(...TRUNCATED) |
[{"role":"system","content":"You are an autonomous coding agent running on the user's machine.\n\nYo(...TRUNCATED) |
Dataset Description
This dataset contains 1,000 coding and reasoning traces generated by the new Fable 5.1 model using max reasoning effort.
It holds almost 30,000,000 tokens of step-by-step chain-of-thought programming across multiple complex domains.
It has also been deduplicated and filtered to remove low-quality traces, keeping only high-quality traces.
Dataset Statistics
| Metric | Value |
|---|---|
| Total Examples | 1,000 Traces |
| Total Token Count | ~30,000,000 Tokens |
| Total Dataset Size | 109 MB |
| Average Trace Size | 109 KB |
| Average Token Count | ~30,000 Tokens |
Dataset Contents & Coverage
The dataset includes step-by-step problem-solving for complex coding tasks, including:
Algorithm design, implementation, and performance optimization.
Advanced debugging and error-handling.
Multi-step logic design and compliance with complex prompt constraints.
Uses
Distilling Fable 5.1 coding and reasoning capabilities down to smaller LLMs.
Improve general coding and reasoning quality.
Teach models to generate clear chain-of-thought steps before outputting their final answer.
- Downloads last month
- -