harness-hub/Qwen3.8-27B-pi-adapted
AI model by harness-hub
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
A LoRA adapter for Qwen/Qwen3.8-27B, trained with reinforcement learning to work as the model behind the pi coding agent on software-engineering and terminal tasks. Full recipe will be shared in the release blogpost for anyone to build their own harness adapter. Pick your setup [](#results) [](#use-with-transformers) [](#use-with-pi) [](#use-with-llama-cpp) [](#run-with-llama-app) [](https://huggingface.co/harness-hub/Qwen3.8-27B-pi-GGUF) [](#merge) [](#training) A real SWE-bench Pro task under pi: the base model searches and re-runs snippets until it hits the 100-step limit; this adapter finds the function, edits it, runs the tests and fixes the last case, in 8 tool calls. Still version, and the task Task: instanceansibleansible-d62496fe416623e88b90139dc7917080cb04ce70 from SWE-bench Pro (hard 51), fix humantobytes. Both runs are from the evaluation above: the base model was graded 0, this adapter 1. Each line is one tool call as the trajectory recorded it, cut to fit. Full paired results (intervals, sign tests, tool calls on the tasks both solved) Evaluated with…
Read the full model card ↗ · Preview checked 2026-11-18T09:43:40.403Z
Inside the original model card — Document outline
- Results
- Use with pi
- 1. Serve the adapter with vLLM
- 2. Point pi at it
- Use with pi (transformers serve)
- Use with pi (llama.cpp)
- Run it with Llama.app (macOS)
- Merge the adapter into the base model
- Training
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
harness-hub/Qwen3.8-27B-pi-adapted is a task-unspecified model repository published by harness-hub on Hugging Face. The source reports the peft library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- Not reported
- Library
- peft
- Recent downloads (30 days)
- 0
- Cumulative likes
- 195
- Hugging Face trending score
- 194
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-11-16T06:52:31.000Z
- Last modified
- 2026-11-17T08:33:55.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: Qwen/Qwen3.8-27B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-18T06:59:26.317Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.