|
Download README.md from lyffseba/pingi: direct link, hf CLI and curl.
- Browser
- Download file 2.52 kB
-
https://huggingface.co/lyffseba/pingi/resolve/main/README.md
- Command line
-
hf download hf://lyffseba/pingi/README.md
-
curl -L -o README.md https://huggingface.co/lyffseba/pingi/resolve/main/README.md
2.52 kB
| base_model: thinkingmachines/Inkling-2-Mini | |
| license: apache-2.0 | |
| tags: | |
| - pi | |
| - inkling-2-mini | |
| - tinker | |
| - harbor | |
| - rl | |
| - agents | |
| - coding | |
| # PINGI — Pi-Native `Inkling-2-Mini` | |
| **PINGI** is an ongoing project adapting [`thinkingmachines/Inkling-2-Mini`](https://huggingface.co/thinkingmachines/Inkling-2-Mini) | |
| (26.4B total / 3.4B active / 5.4B effective across its 3-pass looped MoE core, 1M context, multimodal, Apache 2.0) | |
| specifically for the [`pi`](https://pi.dev/) coding agent harness (`read`, `bash`, `edit`, `write`). | |
| ## Links | |
| - Code, training & eval stack: https://github.com/lyffseba/pingi | |
| - Smoke-test checkpoint (`pingi-smo`): https://huggingface.co/lyffseba/pingi-smo | |
| - Companion architecture research (`xai`): https://huggingface.co/spaces/lyffseba/xai · https://huggingface.co/datasets/lyffseba/xai-studies | |
| ## Current Status | |
| | Stage | Status | Checkpoint / Target | | |
| |---|---|---| | |
| | **Smoke (`pingi-smo`)** | Completed (3 steps, local Docker) | Published on Tinker: `tinker://e7bba24a-6366-5c8c-93b8-21e624a621a6:train:0/sampler_weights/final` ([record](https://huggingface.co/lyffseba/pingi-smo)) | | |
| | **Pilot (`pingi-pilot`)** | Next (640 rollouts, `scale800 + termgrade`, Modal) | *Pending* | | |
| | **MVP / Full (`pingi`)** | Planned (1,600–5,120 rollouts + paired held-out gate) | *Pending* | | |
| *Note: Thinking Machines currently disables raw checkpoint file downloads for `thinkingmachines/Inkling-2-Mini` (`403`). Trained checkpoints are published directly via Tinker (`publish_checkpoint_from_tinker_path`).* | |
| ## Reference Comparison Benchmark | |
| Our primary apples-to-apples target is [`harness-hub/Qwen3.8-27B-pi-adapted`](https://huggingface.co/harness-hub/Qwen3.8-27B-pi-adapted) | |
| (same `pi` harness, same `scale800-harbor` + `termgrade-train-harbor` dataset mixture, thinking OFF, LoRA r=32): | |
| | Model | Active / Total | Thinking | Terminal-Bench 2.1 (`pi`) | SWE-bench Pro hard-51 (`pi`) | | |
| |---|---:|---|---:|---:| | |
| | `Qwen/Qwen3.8-27B` (base) | 27B / 27B | off | 39.5% | 39.2% | | |
| | `harness-hub/Qwen3.8-27B-pi-adapted` | 27B / 27B | off | **55.8%** (+16.3 pts) | **64.7%** (+25.5 pts) | | |
| | `thinkingmachines/Inkling-2-Mini` (official card) | 3.4B (5.4B eff.) / 26.4B | default | 71.6% (`pi v0.83.0`) | 77.9% (`mini-swe-agent`) | | |
| | **PINGI (`lyffseba/pingi`)** | 3.4B (5.4B eff.) / 26.4B | **`none` (default)** | *pending held-out `pingi-eval`* | *pending held-out `pingi-eval`* | | |
| Paired held-out scores will be added here only after `pingi-eval compare_with_base=True` passes the release gate. | |