Text Generation
Transformers
rotorquant
kv-cache-quantization
mistral
Mixture of Experts
lean4
formal-proofs
quantized
Instructions to use majentik/Leanstral-RotorQuant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use majentik/Leanstral-RotorQuant with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="majentik/Leanstral-RotorQuant")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("majentik/Leanstral-RotorQuant", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use majentik/Leanstral-RotorQuant with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "majentik/Leanstral-RotorQuant" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "majentik/Leanstral-RotorQuant", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/majentik/Leanstral-RotorQuant
- SGLang
How to use majentik/Leanstral-RotorQuant 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 "majentik/Leanstral-RotorQuant" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "majentik/Leanstral-RotorQuant", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "majentik/Leanstral-RotorQuant" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "majentik/Leanstral-RotorQuant", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use majentik/Leanstral-RotorQuant with Docker Model Runner:
docker model run hf.co/majentik/Leanstral-RotorQuant
docs: add status notice
Browse files
README.md
CHANGED
|
@@ -13,6 +13,10 @@ library_name: transformers
|
|
| 13 |
pipeline_tag: text-generation
|
| 14 |
---
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
# Leanstral-RotorQuant
|
| 17 |
|
| 18 |
**RotorQuant KV cache compression** for [mistralai/Leanstral-2603](https://huggingface.co/mistralai/Leanstral-2603).
|
|
|
|
| 13 |
pipeline_tag: text-generation
|
| 14 |
---
|
| 15 |
|
| 16 |
+
> [!NOTE]
|
| 17 |
+
> **Status (2026-07-07): no weights published yet.** This repository currently contains only the model card — it marks a planned variant that has not been released. Follow the repo to be notified when files land.
|
| 18 |
+
<!-- status-note -->
|
| 19 |
+
|
| 20 |
# Leanstral-RotorQuant
|
| 21 |
|
| 22 |
**RotorQuant KV cache compression** for [mistralai/Leanstral-2603](https://huggingface.co/mistralai/Leanstral-2603).
|