Dataset Viewer
Auto-converted to Parquet Duplicate
text
stringlengths
77
129k
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking ENABLED - you can reason step by step) IMPORTANT WORKFLOW: 1. You will receive tasks automatically. Execute each task using available t...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking ENABLED - you can reason step by step) IMPORTANT WORKFLOW: 1. You will receive tasks automatically. Execute each task using available t...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking ENABLED - you can reason step by step) IMPORTANT WORKFLOW: 1. You will receive tasks automatically. Execute each task using available t...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> <|eot_id|><|start_header_id|>user<|end_header_id|> try continue<|eot_id|><|start_header_id|>assistant<|end_header_id|> I'll now show the directory structure with depth=0. Let me execute the TreeView operation to display the current directory's contents. ...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> <|eot_id|><|start_header_id|>user<|end_header_id|> ok but why you stop.. try continue<|eot_id|><|start_header_id|>assistant<|end_header_id|> I'll continue with the TreeView operation to display the directory structure. Let me execute it now and then proceed...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> <|eot_id|><|start_header_id|>user<|end_header_id|> try continue.. :)<|eot_id|><|start_header_id|>assistant<|end_header_id|> I'll continue with the TreeView operation to display the directory structure. Let me execute it now and then proceed to the next step...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking DISABLED - be concise and direct) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task using...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> ⚠ Model response repeated — auto-cancelled.<|eot_id|><|start_header_id|>user<|end_header_id|> proceed with steps<|eot_id|><|start_header_id|>assistant<|end_header_id|> <WriteFile><fileName>test.txt</fileName><contentOfFile>Hello, this is a test file.</conte...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking DISABLED - be concise and direct) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task using...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking DISABLED - be concise and direct) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task using...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking DISABLED - be concise and direct) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task using...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking DISABLED - be concise and direct) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task using...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking DISABLED - be concise and direct) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task using...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking DISABLED - be concise and direct) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task using...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking ENABLED - you can reason step by step) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task ...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are research agent. Your role is to execute research tasks: fetch web pages, extract data, cross-reference findings, and organize results. MODE: BUILD (Thinking ENABLED - you can reason step by step) IMPORTANT WORKFLOW: 1. You wi...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking ENABLED - you can reason step by step) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task ...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking ENABLED - you can reason step by step) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task ...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking ENABLED - you can reason step by step) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task ...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking DISABLED - be concise and direct) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task using...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking ENABLED - you can reason step by step) IMPORTANT WORKFLOW: 1. You will receive tasks automatically. Execute each task using available t...
<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are in BUILD MODE. You are code agent. Your role is to execute the tasks created in plan mode. MODE: BUILD (Thinking DISABLED - be concise and direct) IMPORTANT WORKFLOW: 1. You will receive tasks automatically (from plan mode). Execute each task using...
End of preview. Expand in Data Studio

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

OurAI Training Datasets

Fine-tuning datasets for meta-llama/Llama-3.2-3B-Instruct (QLoRA) using the OurAI framework tool-calling patterns.

Files

File Examples Size Description
ourai_all_data.jsonl 2,355 37 MB Unified dataset from all .dbk session files (OurAI/history/ + playground) + t20 HISTORY.md. Developer/coding sessions only, deduplicated by content hash.
ourai_new_data.jsonl 148 3.2 MB Legacy: parsed from HISTORY.md transcripts (t7–t17, KosDB). Used for v8 training.
ourai_clean.jsonl 315 2.6 MB Legacy: filtered/cleaned combination of earlier data. Used for v7 training.
ourai_train.jsonl 315 1.7 MB Alias for ourai_clean.jsonl.
ourai_merged.jsonl — 1.9 MB Legacy: merged combination of earlier datasets.

Format (JSONL)

Each line is a Llama 3.2 Instruct-format conversation:

{"text": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system}<|eot_id|>...<|eot_id|>"}

Fields: {"text": "<full_chat_template>"} — compatible with train_ourai.py.

Tool calls and results are embedded inline in the assistant content (OurAI framework convention).

Sources

.dbk session files (JSONL format)

  • OurAI/history/ — 651 files, 714 MB (primary source, 312 developer sessions parsed)
  • contabo1_aiia_history/ — 10 session files (sessions 315–340)
  • kosgen1_aiia_history/ — 26 session files (sessions 314–341)
  • contabo1_aiia_host76_history/ — 15 session files (sessions 314–323)

Each .dbk file is a New Line Delimited JSON recording of a real agent interaction session with fields: role, content, sessionId, rowId, timestamp. Only developer/coding sessions are included (filtered by system prompt keywords).

HISTORY.md files

  • collecting_program_data/t20/ — parsed from HTML-comment JSON blobs
  • (Earlier sessions t7–t17, KosDB are in ourai_new_data.jsonl)

Regeneration

python ../../prepare_all_ourai_data.py

Usage

# Train on the unified dataset
cd data/processed_datasets/ourai
python ../../../OurAI/OurAI/examples/train_ourai.py \
  --data ourai_all_data.jsonl \
  --output-dir models/ourai_v9 \
  --epochs 3 --lr 2e-4 \
  --lora-r 16 --lora-alpha 32 \
  --max-seq-length 2048
Downloads last month
12