---
license: apache-2.0
language:
- en
base_model:
- allura-org/Lune-Mamba-3B-v1
tags:
- conversational
- instruct
- mamba
- hybrid
---

![image](https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/u1z2dZautKQqCxhDPkw1C.png)
there was originally going to be a better logo but i couldnt get any image model working. so this is what you all deserve

---

#### Info

Lune Mamba 3B GRPO_IF is a Claude-OSS series model based on Granite 4.0 H(ybrid) Micro.

Claude-OSS is a (non-affiliated with Anthropic!) attempt to replicate the style of Anthropic's Claude model on top of open source bases.

*Benchmarks* | Granite 4.0 H Micro | Lune Mamba 3B | Lune Mamba 3B GRPO_IF
-|-|-|-
MMLU|63.7860|*64.2338*|**64.3443**
IFEval*|**80.2218**|75.0462|*77.4492*
<small>* IFEval numbers calculated from prompt loose accuracy </small>

#### Artifacts
- SFT checkpoint: [allura-forge/claumba-micro-sft](/allura-forge/claumba-micro-sft)
- KTO checkpoint: [allura-org/Lune-Mamba-3B-v1](/allura-org/Lune-Mamba-3B-v1)
- GRPO (on IFeval) checkpoint: You are here!