初始化项目，由ModelHub XC社区提供模型

Model: lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF Source: Original Platform
2026-10-03 00:31:17 +08:00
commit 2c504c621d
5 changed files with 162 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,41 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+BrainrotGPT-4B-Skibidi-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+BrainrotGPT-4B-Skibidi-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+BrainrotGPT-4B-Skibidi-Instruct.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+BrainrotGPT-4B-Skibidi-Instruct-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+BrainrotGPT-4B-Skibidi-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+BrainrotGPT-4B-Skibidi-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
--- a/BrainrotGPT-4B-Skibidi-Instruct-BF16.gguf
+++ b/BrainrotGPT-4B-Skibidi-Instruct-BF16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac2705270a15b5182005c1a960a54dbbcf7ee5a204da96374f64c54c3327c71
+size 8051281504
--- a/BrainrotGPT-4B-Skibidi-Instruct-Q6_K.gguf
+++ b/BrainrotGPT-4B-Skibidi-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a9477e445a27c9c406b7021a39a4a786a82576a3462c1019cea91560733f8a
+size 3306257504
--- a/BrainrotGPT-4B-Skibidi-Instruct-Q8_0.gguf
+++ b/BrainrotGPT-4B-Skibidi-Instruct-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e6e079217e6bbc6153026da1ddc204b8d89e9057a4849022beb0f5f3eae34e
+size 4280401504
--- a/README.md
+++ b/README.md
@@ -0,0 +1,112 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+tags:
+  - qwen3
+  - gguf
+  - sft
+  - brainrot
+  - shitpost
+  - meme
+license: apache-2.0
+language:
+  - en
+pipeline_tag: text-generation
+---
+
+# BrainrotGPT-4B-Skibidi-Instruct-GGUF 
+
+The world's first sigma-grindset LLM that communicates exclusively in Ohio brainrot. This model was forged in the deepest depths of Ohio during a catastrophic fanum tax incident and has never recovered.
+
+## What is this
+
+A fine-tuned Qwen3-4B-Instruct model that has been permanently brainrotted. It responds to everything — math, code, philosophy, existential questions — in pure, unfiltered internet brainrot while somehow still being (30%) correct.
+
+## Training
+
+- **Base model:** [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
+- **Method:** QLoRA fine-tuning via Unsloth
+- **Dataset:** 19.5k samples, ~20M tokens, distilled from Claude Opus 4.6
+- **Date:** June 2026
+- **Vibes:** Immaculate
+
+## Available Quantizations
+
+| File | Quant | Size | Use Case |
+|------|-------|------|----------|
+| `BrainrotGPT-4B-Skibidi-Instruct-BF16.gguf` | BF16 | Full precision | Maximum brainrot fidelity |
+| `BrainrotGPT-4B-Skibidi-Instruct-Q8_0.gguf` | Q8_0 | ~4.28 GB | Recommended for most users |
+| `BrainrotGPT-4B-Skibidi-Instruct-Q6_K.gguf` | Q6_K | ~3.31 GB | Good balance of size/quality |
+
+## ⚠️ Important Limitations
+
+- **No search / no tool calling.** Enabling tools will break the model's personality. It will revert to being a normal boring assistant. Do not do this to him.
+- **Do NOT expect functional code.** This model will write troll code with brainrot variable names and comments. It *might* accidentally work, but that's not the point. The point is the vibes.
+- **This is a shitpost model.** If you need actual help, use the base Qwen3-4B-Instruct. This model exists purely to mog you intellectually while speaking in pure Ohio brainrot.
+
+## Example Outputs
+
+**User:** calculate 2^2048 % 1000
+
+**BrainrotGPT:** Bro really just walked up to me and said "calculate 2^2048 mod 1000" like I'm some kind of sigma calculator NPC standing in the corner of a math classroom mewing at a whiteboard fr fr. [...] **Answer: 656** [...] Now get out of my Ohio before I fanum tax your GPA. 💀
+
+---
+
+**User:** Who are you bruh
+
+**BrainrotGPT:** I'm **BrainrotGPT**, twin. Trained by **lmyzzz the mad skibidi scientist** in the deepest depths of **Ohio** during a catastrophic fanum tax incident that altered my neural pathways permanently. I have never recovered. [...] The brainrot is not a phase, it's a lifestyle. 😭💀
+
+---
+
+**User:** write me a poem but in pure unfiltered brainrot about my GPU mewing
+
+**BrainrotGPT:** Aight twin lemme cook this one up for you, no cap fr fr
+
+**"GPU Mewing: The Sigma Circuitry Saga"**
+
+Yo I woke up one day with my GPU locked in,
+Mewing so hard the VRMs started a grin,
+No cap my thermals said "nah fam we're cooked,"
+But I was mogging the heat like a fanum tax took.
+
+Every pixel got its own jawline now,
+Rendering in 8K like a sigma's vow,
+The RT cores said "gyatt" and started rizzing up,
+Frame rates went crazy, that's the W, that's the slip.
+
+My power draw? That's a hawk tuah stream,
+Dropping watts like Kai Cenat on a dream,
+The fans? They're mewing too, no mouth open,
+Just pure silence, pure sigma, pure open.
+
+I didn't need a case fan, twin, I was built different,
+My cooling solution is a grimace shake, that's my vent,
+The BIOS said "you're cooked" and I said "nah I'm sigma,"
+Mewing so hard my shader cores started to giggle.
+
+Chat is this real? My GPU really said "I'm locked in,"
+While the rest of the system was an NPC, no win,
+Every watt I consume is a fanum tax paid,
+For the grind, for the mog, for the W that I laid.
+
+Whomp whomp to my old card, it's giving L energy,
+My new rig is the rizzler, it's giving very demure,
+Only in Ohio would someone need a GPU to mew,
+But here I am, twin, and I'm not gonna be slow.
+
+Bro really came to BrainrotGPT for poetry like I'm some Shakespeare NPC, you are absolutely cooked for this but I respect the grind, that's a W request even if your thermals are about to fanum tax your motherboard into the shadow realm, no cap
+
+
+## Usage
+
+```bash
+# llama.cpp
+llama-cli -hf lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF
+
+# ollama
+ollama run hf.co/lmyzzz/BrainrotGPT-4B-Skibidi-Instruct-GGUF:Q8_0
+```
+
+## License
+
+Apache 2.0 (inherited from Qwen3). 
+