Fix model card accuracy (format/filename)

README.md

@@ -0,0 +1,44 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+  - lora
+  - peft
+  - adapter
+  - qwen2
+  - forkjoin-ai
+  - buleyean
+base_model: Qwen/Qwen2.5-32B-Instruct
+pipeline_tag: text-generation
+---
+
+# Buleyean Qwen2.5-32B — Builder (LoRA adapter)
+
+> **LoRA adapter** for [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) — the *builder* personality from the Buleyean affective-RL series. Powered by [Aether](https://github.com/forkjoin-ai/aether) / [Edgework.ai](https://edgework.ai).
+
+## Details
+
+| Property | Value |
+|----------|-------|
+| Type | LoRA adapter (PEFT) |
+| Base model | [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) |
+| Personality | builder |
+| Adapter | `lora/adapter_model.safetensors` |
+| License | apache-2.0 |
+
+## Usage
+
+```python
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
+model = PeftModel.from_pretrained(base, "forkjoin-ai/buleyean-qwen2.5-32b-builder", subfolder="lora")
+tok = AutoTokenizer.from_pretrained("forkjoin-ai/buleyean-qwen2.5-32b-builder", subfolder="lora")
+```
+
+## About
+
+Published by [AFFECTIVELY](https://huggingface.co/forkjoin-ai) · Managed by [@buley](https://huggingface.co/buley).
+
+- [All models](https://huggingface.co/forkjoin-ai) · [GitHub](https://github.com/forkjoin-ai) · [Edgework.ai](https://edgework.ai)