Downloads Β· 30 days
18
18% of all-time downloads
PIPer-iclr/PIPer-8B
PIPer-8B is a text generation model from PIPer-iclr. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
Downloads Β· 30 days
18
18% of all-time downloads
All-time downloads
100
Public
Parameters
8.2B
32.8 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors32.8 GB Β· 100%
From the Hugging Face model README
Democratizing environment setup with on-device sized models that match the performance of much larger proprietary systems
</div>Environment setupβthe process of configuring systems to work with specific software projectsβremains a persistent challenge in software engineering. PIPer addresses this by training specialized on-device models that can automatically generate correct Bash scripts for environment configuration.
Our approach combines:
| Model | Size | EnvBench avg@5 | Cost per 1M tokens |
|---|---|---|---|
| PIPer | 8B | 19.4 | $0.60 |
| GPT-4o | - | 19.4 | $15.00 |
| Qwen3-32B | 32B | 16.2 | $2.00 |
| Qwen3-8B | 8B | 2.6 | $0.60 |
π PIPer achieves 9Γ improvement over its base model while matching GPT-4o performance at 25x lower cost

| Model | Description | HuggingFace Link |
|---|---|---|
| π PIPer (Full) | Complete SFT+RL trained model | PIPer-iclr/PIPer-8B |
| π― PIPer (RL-only) | RLVR checkpoint only | PIPer-iclr/PIPer-8B-RL-only |
| π PIPer (SFT-only) | Supervised fine-tuning only | PIPer-iclr/PIPer-8B-SFT-only |
| Dataset | Description | HuggingFace Link |
|---|---|---|
| EnvBench Zero-shot RL | Training prompts and evaluation data | PIPer-iclr/envbench-zeroshot-rl |
| Benchmark | Description | Metric | Our Result |
|---|---|---|---|
| EnvBench-Python | 329 Python repositories | pass@5 | π 27/329 |
| Repo2Run | 420 Python repositories | pass@5 | π 103/420 |
| Terminal-Bench | 80 terminal tasks | pass@10 | 4/80 |
This project is licensed under the MIT License - see the LICENSE file for details.