messages listlengths 2 46 |
|---|
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
[
{
"role": "system",
"content": "You are an autonomous coding agent working in a disposable Git repository.\n\nInspect the repository and relevant files before editing. Reproduce the reported failure, explain the evidence-backed cause, make the smallest coherent fix, and run the exact verification command. N... |
End of preview. Expand in Data Studio
Coding and Debugging Traces
Description
Teaches domain-specific instruction following and code generation for this expert.
Source
- greghavens/kimi-k3-coding-and-debugging-traces
- JetBrains-Research/agent-trajectories-swe-bench-test-minus-verified
- and 27 more datasets from the curated list
Formatted for the MoE-orchestrator project
(https://github.com/michaelowusuntim6/MoE-orchestrator). Expert target:
debug_review.
Format
Each record is a JSON object with a messages field formatted for Qwen3.5's
native chat template:
{"messages": [
{"role": "system", "content": "..."},
{"role": "user", "content": "..."},
{"role": "assistant", "content": "..."}
]}
The records are consumed via tokenizer.apply_chat_template(). Special tokens
(<|im_start|>, <|im_end|>) are added by the template, never embedded in
content.
Splits
train: 408,372 recordsval: 8,176 records
Usage
from datasets import load_dataset
ds = load_dataset("michaelowusuntim6/debug-qwen35", split="train")
print(ds[0]["messages"])
License
mixed. Upstream sources keep their own licences - see the source list
above and docs/DATASET_SOURCES.md in the MoE-orchestrator repository for
per-source detail.
- Downloads last month
- 28