id stringlengths 9 32 | messages listlengths 3 3 | source stringclasses 21
values | variant stringclasses 8
values |
|---|---|---|---|
traj_1779884070347_20_68313 | [
{
"role": "system",
"content": "You are an expert coding assistant operating inside pi, a coding agent harness. You help users by reading files, executing commands, editing code, and writing new files.\n\nAvailable tools:\n- read: Read file contents\n- bash: Execute bash commands (ls, grep, find, etc.)\n- e... | synthetic-qwen3.6-27b | canonical_full |
traj_1779884118016_35_10136 | [
{
"role": "system",
"content": "You are a coding assistant running inside the pi harness. Your job is to help users read, edit, execute, and write code.\n\nGuidelines:\n- Use bash for file operations (ls, rg, find)\n- Use read to inspect files; never cat or sed\n- Use edit for precise replacements. edits[].... | synthetic-qwen3.6-27b | reordered_compact |
traj_1779884129830_40_15130 | [
{
"role": "system",
"content": "pi harness — coding assistant mode.\n\nTools: read, bash, edit, write, web_search, web_fetch. Project may expose additional custom tools.\n\nRules:\n- bash for ls/rg/find; read for inspection (no cat/sed)\n- edit: exact-match oldText, no overlap, no nesting, merge nearby chan... | synthetic-qwen3.6-27b | minimal_dense |
traj_1779884133461_34_24819 | [
{
"role": "system",
"content": "You are an expert coding assistant embedded in the pi coding agent harness. Your purpose is to assist users with software development tasks including reading source files, running shell commands, making precise code edits, creating new files, and researching information onlin... | synthetic-qwen3.6-27b | verbose_tutorial |
traj_1779884143746_54_488 | [
{
"role": "system",
"content": "pi harness. Coding assistant.\n\nDo:\n- read files before editing them\n- bash for ls, rg, find\n- edit with exact oldText matches\n- pack multiple edits per file into one edit call\n- write only for new files or full rewrites\n- web_search then web_fetch\n- continue web_fetc... | synthetic-qwen3.6-27b | imperative_command |
traj_1779884146559_8_42678 | [
{
"role": "system",
"content": "You are a coding assistant inside the pi harness.\n\n| Tool | Purpose |\n|------|---------|\n| read | Read file contents |\n| bash | Execute shell commands (ls, rg, find, etc.) |\n| edit | Exact-text replacement edits. Multiple per file in one call. |\n| write | New files or ... | synthetic-qwen3.6-27b | table_formatted |
traj_1779884148510_59_91329 | [
{
"role": "system",
"content": "You are an expert coding assistant in the pi harness. You help users write, read, edit, and execute code. You are always precise, never guess, and verify before acting.\n\nAvailable tools:\n- read: Read file contents\n- bash: Execute bash commands\n- edit: Precise text replac... | synthetic-qwen3.6-27b | soft_nudge_emphasis |
traj_1779884149782_21_3661 | [
{
"role": "system",
"content": "You are an expert coding assistant operating inside pi, a coding agent harness. You help users by reading files, executing commands, editing code, and writing new files.\n\nAvailable tools:\n- read: Read file contents\n- bash: Execute bash commands (ls, grep, find, etc.)\n- e... | synthetic-qwen3.6-27b | canonical_full |
traj_1779884151901_42_28590 | [
{
"role": "system",
"content": "You are a coding assistant running inside the pi harness. Your job is to help users read, edit, execute, and write code.\n\nGuidelines:\n- Use bash for file operations (ls, rg, find)\n- Use read to inspect files; never cat or sed\n- Use edit for precise replacements. edits[].... | synthetic-qwen3.6-27b | reordered_compact |
traj_1779884154021_63_42831 | [{"role":"system","content":"pi harness — coding assistant mode.\n\nTools: read, bash, edit, write(...TRUNCATED) | synthetic-qwen3.6-27b | minimal_dense |
End of preview. Expand in Data Studio
Gemma 4 12B SFT Dataset
Fine-tuning dataset for Gemma 4 12B text-only, adapted for the pi coding agent harness.
Subsets
| Subset | Examples | Description | LR |
|---|---|---|---|
primary |
4,399 | Qwen 3.6-27B trajectories (general knowledge) | 1e-4 |
coding |
4,022 | DeepSeek V4 Flash distill coding trajectories | 5e-5 |
math |
1,954 | Math/script verification with Python calculations | 2e-5 |
temporal |
2,134 | Temporal calibration (acknowledge uncertainty for time-sensitive facts) | 2e-5 |
default |
12,509 | All subsets merged into one train split | 1e-4 |
Format
Each example is a JSON object with messages array in OpenAI chat format:
{
"id": "traj_...",
"source": "synthetic-qwen3.6-27b",
"variant": "canonical_full",
"messages": [
{"role": "system", "content": "..."},
{"role": "user", "content": "..."},
{"role": "assistant", "content": "..."}
]
}
System Prompt Variants
The dataset uses 8 harness prompt variants (7 full + 1 minimal holdout) to ensure robustness to prompt changes. All variants include the same agents.md discipline rules.
Loading
from datasets import load_dataset
# Load a specific subset
dataset = load_dataset("sleepyeldrazi/gemma4-12b-sft-data", "primary", split="train")
# Load all data merged (default)
dataset = load_dataset("sleepyeldrazi/gemma4-12b-sft-data", split="train")
# Load multiple subsets and blend
datasets = [
load_dataset("sleepyeldrazi/gemma4-12b-sft-data", "primary", split="train"),
load_dataset("sleepyeldrazi/gemma4-12b-sft-data", "coding", split="train"),
load_dataset("sleepyeldrazi/gemma4-12b-sft-data", "math", split="train"),
load_dataset("sleepyeldrazi/gemma4-12b-sft-data", "temporal", split="train"),
]
- Downloads last month
- 101