penfever/

exp_rpt_stack-junit-v6-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/penfever/exp_rpt_stack-junit-v6-qwen3.5-122b-131k-opencode-traces.