Add 8 courtroom jargon-style LoRAs (GGUF) for MiniCPM5-1B

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+style-ai.lora.gguf filter=lfs diff=lfs merge=lfs -text
+style-aviation.lora.gguf filter=lfs diff=lfs merge=lfs -text
+style-corporate.lora.gguf filter=lfs diff=lfs merge=lfs -text
+style-gaming.lora.gguf filter=lfs diff=lfs merge=lfs -text
+style-medical.lora.gguf filter=lfs diff=lfs merge=lfs -text
+style-politics.lora.gguf filter=lfs diff=lfs merge=lfs -text
+style-scifi.lora.gguf filter=lfs diff=lfs merge=lfs -text
+style-sports.lora.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+license: apache-2.0
+base_model: openbmb/MiniCPM5-1B
+tags:
+  - lora
+  - gguf
+  - llama.cpp
+  - text-generation
+language:
+  - en
+---
+
+# Buzzwords & Misdemeanors — style LoRAs
+
+Eight GGUF LoRA adapters for **`openbmb/MiniCPM5-1B`** (apply with `llama.cpp`, no merge),
+one per jargon *style*. They turn the base model into a courtroom actor (judge / prosecutor
+/ defense — selected by system prompt) that argues in dense domain jargon while never naming
+the hidden profession or charge in plain words.
+
+Built for the Hugging Face **Build Small** hackathon. See the game:
+[BuildSmallHackathon](https://github.com/) · base GGUF: `openbmb/MiniCPM5-1B-GGUF`.
+
+## Adapters
+`style-{corporate, aviation, ai, politics, medical, gaming, sports, scifi}.lora.gguf`
+
+## How they were trained
+- **Teacher distillation:** Gemma 4 31B (FP8) generated ShareGPT courtroom transcripts,
+  anchored by curated per-style jargon banks and seeded for variety.
+- **Curriculum fork:** stage 1 trains a generic legal LoRA (`legal_base`) on MiniCPM5-1B;
+  stage 2 forks each style from it (fresh run, same config) — never merged into the base.
+- Each adapter benchmarked vs the base (think-mode off): all 8 PASS — high target-jargon
+  coverage, peaking on their own style.
+
+## Usage (llama.cpp)
+```bash
+# base + one style adapter
+llama-cli -m MiniCPM5-1B-Q4_K_M.gguf --lora style-corporate.lora.gguf -p "..."
+```

style-ai.lora.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79280f6967f203b89afc301f689da5d491c3e933c535b862260b388d485fbffa
+size 89676768

style-aviation.lora.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19fd70cc4a1bf268e0ea0a16efee20cdee1b1672e294a14cb2ac62f6eecde4ac
+size 89676768

style-corporate.lora.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0bab14e8ac1b68a66ee8416bd9841bf0a652abec47e62581bfec706ddc3674
+size 89676768

style-gaming.lora.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3c9437c5972c7143f16fe21887d2490dc8a9303f25af4466bd4d6f7035c1c5
+size 89676768

style-medical.lora.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6e077454e84349a05f09026fd452f8bd019be551c874384f57dc5576ae495e
+size 89676768

style-politics.lora.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec2d5e8b47bfb89b1abb5660dd1d06ce4eef7201351f28a4e6ddd4353afa040
+size 89676768

style-scifi.lora.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022bbf079d764e77fab895b81c2f3b7c9dc1338f1ba97a67416950ba33f25a0b
+size 89676768

style-sports.lora.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd3dc900ded99ce48ea646cfefa79d2d8386b4f2322c806bad6245554dd01bc
+size 89676768