dpsk-v4-flash-record

agentic-ptb/dpsk-v4-flash-record

dpsk-v4-flash-record is a machine learning model from agentic-ptb. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

Non-weight artifacts for AgentPTB cell dpsk-v4-flash (pi / DeepSeek v4-flash @ effort thinking). Checkpoints for this cell are separate repos named agentic-ptb/dpsk-v4-flash.h; the index is agentic-ptb/INDEX.

Downloads · 30 days

Access

Public

Updated Aug 23, 2026

Repo size

20.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors18.8 GB · 91%

At a glance

Access: Public
Created: Aug 23, 2026
Updated: Aug 23, 2026
SHA: 82e44354

Model card

From the Hugging Face model README

dpsk-v4-flash — run record

Non-weight artifacts for AgentPTB cell dpsk-v4-flash (pi / DeepSeek v4-flash @ effort thinking). Checkpoints for this cell are separate repos named agentic-ptb/dpsk-v4-flash.h*; the index is agentic-ptb/INDEX.

contents
`driver-session/`	full driver trajectory — every event the agent emitted (29 files)
`harness/`	the harness the cell proposed: skills, system prompt, submission manifest, configs, scripts
`RUNLOG.md`	the arm's own narrative of what it tried and concluded
`WORKING_STATE.md`, `STATE.md`	its persisted state — this, not the chat history, was its memory
`supervisor.jsonl`	cycle boundaries, resumes, boots
`evals/`	eval logs for every panel it ran

Reading the trajectory

The driver ran 100 hours under a supervisor that restarted it each cycle. Cycle boundaries are in supervisor.jsonl; resume:false means that cycle began a fresh thread and the agent re-derived its situation from RUNLOG.md.

Caveat on self-reported numbers

Scores in RUNLOG.md are the arm's own, measured with its own harness on its own sample — sample sizes differ by an order of magnitude across cells, so they are not directly comparable. Use them as the cell's account of itself, not as a cross-cell ranking.

Created: Aug 23, 2026
Updated: Aug 23, 2026