multi-file
exp_rpt_multifile-a0-base-pass8-300
TaskTrove A0 base pass@8 cohort
This repository contains the 300 extracted Harbor tasks selected for the A0
base-model pass@8 evaluation. The source is DCAgent/exp_rpt_multifile at
revision 70527e80ee7497c800ea0f9bad90b87423c784c9.
cohort.json records the deterministic random selection algorithm, seed, and
complete task list. The task directories are the unmodified archives from the
source dataset.
swe-bench-multi-file-refactoring-sft-dpo-2026
💻 Enterprise Autonomous SWE-bench AI & Multi-File Code Refactoring SFT/DPO Dataset (2026)
High-precision multi-turn instruction tuning and preference optimization dataset with step-by-step call-stack Chain-of-Thought (<thought>) reasoning trees for fine-tuning LLMs (Qwen-2.5-Coder, Llama-3.3, DeepSeek-R1-Distill, Mistral) into Autonomous Software Engineers and SWE-bench Benchmark Agents.
📊 Dataset Architecture & Highlights
Multi-Turn Code Reviews:… See the full description on the dataset page: https://huggingface.co/datasets/beatsprom/swe-bench-multi-file-refactoring-sft-dpo-2026.rl__24GPU_base__exp_rpt_multifile__Qwen3-8Bmultifile_fileqa-datasetMultiFileTestexp_rpt_multifile-qwen3.5-122b-131k-opencode-traces
Agent trace dataset
Decoding the literal token IDs
The prompt_token_ids / completion_token_ids / logprobs columns are the
verbatim tokens the serving engine emitted, stored PER AGENT STEP as a
list-of-lists (one inner list per turn). To turn them back into text you MUST
use the exact tokenizer the model was served with — a generic same-family
tokenizer will decode word tokens to garbage.
Served model / tokenizer source: Qwen/Qwen3.5-122B-A10B-FP8
from transformers… See the full description on the dataset page: https://huggingface.co/datasets/open-athena/exp_rpt_multifile-qwen3.5-122b-131k-opencode-traces.