---
license: mit
base_model: zai-org/GLM-4.5-Air
tags:
  - agentic-search
  - retrieval
  - memory
  - tool-use
  - lora
  - glm
library_name: transformers
pipeline_tag: text-generation
---

# Rolodex-12B

Rolodex-12B (12B active / 106B total MoE parameters, GLM-4.5-Air derivative) is
a search model: fine-tuned for agentic, tool-driven retrieval over personal and
team knowledge bases — multi-step search, memory lookup, and evidence
synthesis with tool use.

## Lineage

1. **Base**: [zai-org/GLM-4.5-Air](https://huggingface.co/zai-org/GLM-4.5-Air) (MIT)
2. **This model**: LoRA fine-tune (r=32, α=64) with OAPL on agentic search
   trajectories, merged into the base weights.

This repo contains the fully merged weights, plus the LoRA adapter under
`adapter/`. Because the base is the public GLM-4.5-Air, the adapter can also be
applied directly to the base model (see `adapter/README.md`, including the
router-bias step).

Rolodex-12B is also the stage-1 base of
[PolyClerk-12B](https://huggingface.co/polygramme/PolyClerk-12B), our legal
work-product model.

## Training

| | |
|---|---|
| Method | OAPL, LoRA r=32 / α=64 (merged) |
| Framework | ms-swift (Megatron backend) |
| Epochs | 1 |

## Evaluation

On internal short-factoid retrieval QA over indexed knowledge bases, the
OAPL-trained model improves materially over the GLM-4.5-Air base while using
single-tree guided search (fewer tool calls than majority-vote baselines).
Internal numbers; independent benchmarks pending.

## Usage

Requires ~200GB of weights (bf16). Serve with vLLM:

```bash
vllm serve polygramme/Rolodex-12B --tensor-parallel-size 4 --max-model-len 131072
```

The chat template is included (`chat_template.jinja`). The model is trained for
tool-use loops (search/read tools) — it performs best inside an agentic harness
that exposes retrieval tools, rather than as a plain chat model.

## Intended use & limitations

Intended for retrieval-augmented and memory-augmented agent workloads. It may
underperform general instruction models on open-ended chat. Verify retrieved
claims against sources; the model can still hallucinate under sparse retrieval.

## License

MIT, following the GLM-4.5-Air base license. © the model authors.