Instructions to use polygramme/Rolodex-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use polygramme/Rolodex-12B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="polygramme/Rolodex-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("polygramme/Rolodex-12B")
model = AutoModelForCausalLM.from_pretrained("polygramme/Rolodex-12B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use polygramme/Rolodex-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "polygramme/Rolodex-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "polygramme/Rolodex-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/polygramme/Rolodex-12B

SGLang

How to use polygramme/Rolodex-12B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "polygramme/Rolodex-12B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "polygramme/Rolodex-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "polygramme/Rolodex-12B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "polygramme/Rolodex-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use polygramme/Rolodex-12B with Docker Model Runner:
```
docker model run hf.co/polygramme/Rolodex-12B
```

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

Base: zai-org/GLM-4.5-Air (MIT)
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, 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:

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

Downloads last month: 330

Safetensors

Model size

110B params

Tensor type

F32

BF16

Model tree for polygramme/Rolodex-12B

Base model

zai-org/GLM-4.5-Air

Adapter

(7)

this model

Adapters

1 model