|
|
| # PPP-36B |
|
|
| A Seed-OSS-36B-Instruct (https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct) model trained to localize function names in a repository (SWE-Func-Loc) and interact with users in a proactive and personalized way. |
|
|
| **Paper:** Training Proactive and Personalized LLM Agents (https://arxiv.org/pdf/2511.02208) |
|
|
| **Github:** https://github.com/sunnweiwei/PPP-Agent |
|
|
| ## Serving with vLLM |
|
|
| This model includes bias terms in attention output projections. To serve correctly: |
|
|
| ```bash |
| wget https://huggingface.co/sunweiwei/PPP-36B/resolve/main/patch_seed_oss.py |
| python -c "import patch_seed_oss" && vllm serve sunweiwei/PPP-36B |
| ``` |
|
|
| Or in Python: |
| ```python |
| import patch_seed_oss # Load once after downloading |
| from vllm import LLM |
| |
| llm = LLM("sunweiwei/PPP-36B") |
| ``` |
| The patch reads the attention_out_bias config parameter to properly initialize the model. |
