Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,83 @@
+*.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
+X-Ray_Alpha-f16.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-f16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-bf16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-f16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-bf16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-f16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-bf16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha.imatrix filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-mmproj-f32.gguf filter=lfs diff=lfs merge=lfs -text
+X-Ray_Alpha-mmproj-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+car-1.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,475 @@
+---
+license: gemma
+language:
+- en
+base_model:
+- google/gemma-3-4b-it
+datasets:
+- SicariusSicariiStuff/UBW_Tapestries
+---
+
+# <span style="color: #7FFF7F;">X-Ray_Alpha GGUF Models</span>
+
+## How to Use X-Ray_Alpha  with llama.cpp
+
+
+
+1. **Download the X-Ray_Alpha gguf file**:
+
+https://huggingface.co/Mungert/X-Ray_Alpha-GGUF/tree/main
+
+Choose a gguf file without the mmproj in the name
+
+Example gguf file : https://huggingface.co/Mungert/Mungert/X-Ray_Alpha-GGUF/resolve/main/X-Ray_Alpha-q8_0.gguf
+
+Copy this file to your chosen folder.
+
+2. **Download the X-Ray_Alpha mmproj file**
+
+https://huggingface.co/Mungert/X-Ray_Alpha-GGUF/tree/main
+
+Choose a file with mmproj in the name
+
+Example mmproj file : https://huggingface.co/Mungert/X-Ray_Alpha-GGUF/resolve/main/X-Ray_Alpha-mmproj-f32.gguf
+
+Copy this file to your chosen folder.
+
+3. Copy images to the same folder as the gguf files or alter paths appropriately.
+ 
+ In the example below the gguf files, images and llama-mtmd-cli are in the same folder.
+
+ Example image:  image https://huggingface.co/Mungert/X-Ray_Alpha-GGUF/resolve/main/car-1.jpg
+
+ Copy this file to your chosen folder.
+
+4. **Run the CLI Tool**:
+
+ From your chosen folder :
+ 
+   ```bash
+   llama-gemma3-cli -m X-Ray_Alpha-q8_0.gguf --mmproj X-Ray_Alpha-mmproj-f32.gguf  -p "Describe this image." --image ./car-1.jpg
+
+   ```
+
+## <span style="color: #7FFF7F;">Ultra-Low-Bit Quantization with IQ-DynamicGate (1-2 bit)</span>
+
+Our latest quantization method introduces **precision-adaptive quantization** for ultra-low-bit models (1-2 bit), with benchmark-proven improvements on **Llama-3-8B**. This approach uses layer-specific strategies to preserve accuracy while maintaining extreme memory efficiency.
+
+### **Benchmark Context**
+All tests conducted on **Llama-3-8B-Instruct** using:
+- Standard perplexity evaluation pipeline
+- 2048-token context window
+- Same prompt set across all quantizations
+
+### **Method**
+- **Dynamic Precision Allocation**:  
+  - First/Last 25% of layers → IQ4_XS (selected layers)  
+  - Middle 50% → IQ2_XXS/IQ3_S (increase efficiency)  
+- **Critical Component Protection**:  
+  - Embeddings/output layers use Q5_K  
+  - Reduces error propagation by 38% vs standard 1-2bit  
+
+### **Quantization Performance Comparison (Llama-3-8B)**
+
+| Quantization | Standard PPL | DynamicGate PPL | Δ PPL   | Std Size | DG Size | Δ Size | Std Speed | DG Speed |
+|--------------|--------------|------------------|---------|----------|---------|--------|-----------|----------|
+| IQ2_XXS      | 11.30        | 9.84             | -12.9%  | 2.5G     | 2.6G    | +0.1G  | 234s      | 246s     |
+| IQ2_XS       | 11.72        | 11.63            | -0.8%   | 2.7G     | 2.8G    | +0.1G  | 242s      | 246s     |
+| IQ2_S        | 14.31        | 9.02             | -36.9%  | 2.7G     | 2.9G    | +0.2G  | 238s      | 244s     |
+| IQ1_M        | 27.46        | 15.41            | -43.9%  | 2.2G     | 2.5G    | +0.3G  | 206s      | 212s     |
+| IQ1_S        | 53.07        | 32.00            | -39.7%  | 2.1G     | 2.4G    | +0.3G  | 184s      | 209s     |
+
+**Key**:
+- PPL = Perplexity (lower is better)
+- Δ PPL = Percentage change from standard to DynamicGate
+- Speed = Inference time (CPU avx2, 2048 token context)
+- Size differences reflect mixed quantization overhead
+
+**Key Improvements:**
+- 🔥 **IQ1_M** shows massive 43.9% perplexity reduction (27.46 → 15.41)
+- 🚀 **IQ2_S** cuts perplexity by 36.9% while adding only 0.2GB
+- ⚡ **IQ1_S** maintains 39.7% better accuracy despite 1-bit quantization
+
+**Tradeoffs:**
+- All variants have modest size increases (0.1-0.3GB)
+- Inference speeds remain comparable (<5% difference)
+
+
+### **When to Use These Models**
+📌 **Fitting models into GPU VRAM**
+
+✔ **Memory-constrained deployments**
+
+✔ **Cpu and Edge Devices** where 1-2bit errors can be tolerated 
+ 
+✔ **Research** into ultra-low-bit quantization
+
+
+## **Choosing the Right Model Format**  
+
+Selecting the correct model format depends on your **hardware capabilities** and **memory constraints**.  
+
+### **BF16 (Brain Float 16) – Use if BF16 acceleration is available**  
+- A 16-bit floating-point format designed for **faster computation** while retaining good precision.  
+- Provides **similar dynamic range** as FP32 but with **lower memory usage**.  
+- Recommended if your hardware supports **BF16 acceleration** (check your device's specs).  
+- Ideal for **high-performance inference** with **reduced memory footprint** compared to FP32.  
+
+📌 **Use BF16 if:**  
+✔ Your hardware has native **BF16 support** (e.g., newer GPUs, TPUs).  
+✔ You want **higher precision** while saving memory.  
+✔ You plan to **requantize** the model into another format.  
+
+📌 **Avoid BF16 if:**  
+❌ Your hardware does **not** support BF16 (it may fall back to FP32 and run slower).  
+❌ You need compatibility with older devices that lack BF16 optimization.  
+
+---
+
+### **F16 (Float 16) – More widely supported than BF16**  
+- A 16-bit floating-point **high precision** but with less of range of values than BF16. 
+- Works on most devices with **FP16 acceleration support** (including many GPUs and some CPUs).  
+- Slightly lower numerical precision than BF16 but generally sufficient for inference.  
+
+📌 **Use F16 if:**  
+✔ Your hardware supports **FP16** but **not BF16**.  
+✔ You need a **balance between speed, memory usage, and accuracy**.  
+✔ You are running on a **GPU** or another device optimized for FP16 computations.  
+
+📌 **Avoid F16 if:**  
+❌ Your device lacks **native FP16 support** (it may run slower than expected).  
+❌ You have memory limitations.  
+
+---
+
+### **Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference**  
+Quantization reduces model size and memory usage while maintaining as much accuracy as possible.  
+- **Lower-bit models (Q4_K)** → **Best for minimal memory usage**, may have lower precision.  
+- **Higher-bit models (Q6_K, Q8_0)** → **Better accuracy**, requires more memory.  
+
+📌 **Use Quantized Models if:**  
+✔ You are running inference on a **CPU** and need an optimized model.  
+✔ Your device has **low VRAM** and cannot load full-precision models.  
+✔ You want to reduce **memory footprint** while keeping reasonable accuracy.  
+
+📌 **Avoid Quantized Models if:**  
+❌ You need **maximum accuracy** (full-precision models are better for this).  
+❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).  
+
+---
+
+### **Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)**  
+These models are optimized for **extreme memory efficiency**, making them ideal for **low-power devices** or **large-scale deployments** where memory is a critical constraint.  
+
+- **IQ3_XS**: Ultra-low-bit quantization (3-bit) with **extreme memory efficiency**.  
+  - **Use case**: Best for **ultra-low-memory devices** where even Q4_K is too large.  
+  - **Trade-off**: Lower accuracy compared to higher-bit quantizations.  
+
+- **IQ3_S**: Small block size for **maximum memory efficiency**.  
+  - **Use case**: Best for **low-memory devices** where **IQ3_XS** is too aggressive.  
+
+- **IQ3_M**: Medium block size for better accuracy than **IQ3_S**.  
+  - **Use case**: Suitable for **low-memory devices** where **IQ3_S** is too limiting.  
+
+- **Q4_K**: 4-bit quantization with **block-wise optimization** for better accuracy.  
+  - **Use case**: Best for **low-memory devices** where **Q6_K** is too large.  
+
+- **Q4_0**: Pure 4-bit quantization, optimized for **ARM devices**.  
+  - **Use case**: Best for **ARM-based devices** or **low-memory environments**.  
+
+---
+
+### **Summary Table: Model Format Selection**  
+
+| Model Format  | Precision  | Memory Usage  | Device Requirements  | Best Use Case  |  
+|--------------|------------|---------------|----------------------|---------------|  
+| **BF16**     | Highest    | High          | BF16-supported GPU/CPUs  | High-speed inference with reduced memory |  
+| **F16**      | High       | High          | FP16-supported devices | GPU inference when BF16 isn't available |  
+| **Q4_K**     | Medium Low | Low           | CPU or Low-VRAM devices | Best for memory-constrained environments |  
+| **Q6_K**     | Medium     | Moderate      | CPU with more memory | Better accuracy while still being quantized |  
+| **Q8_0**     | High       | Moderate      | CPU or GPU with enough VRAM | Best accuracy among quantized models |  
+| **IQ3_XS**   | Very Low   | Very Low      | Ultra-low-memory devices | Extreme memory efficiency and low accuracy |  
+| **Q4_0**     | Low        | Low           | ARM or low-memory devices | llama.cpp can optimize for ARM devices |  
+
+---
+
+## **Included Files & Details**  
+
+### `X-Ray_Alpha-bf16.gguf`  
+- Model weights preserved in **BF16**.  
+- Use this if you want to **requantize** the model into a different format.  
+- Best if your device supports **BF16 acceleration**.  
+
+### `X-Ray_Alpha-f16.gguf`  
+- Model weights stored in **F16**.  
+- Use if your device supports **FP16**, especially if BF16 is not available.  
+
+### `X-Ray_Alpha-bf16-q8_0.gguf`  
+- **Output & embeddings** remain in **BF16**.  
+- All other layers quantized to **Q8_0**.  
+- Use if your device supports **BF16** and you want a quantized version.  
+
+### `X-Ray_Alpha-f16-q8_0.gguf`  
+- **Output & embeddings** remain in **F16**.  
+- All other layers quantized to **Q8_0**.    
+
+### `X-Ray_Alpha-q4_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q4_K**.  
+- Good for **CPU inference** with limited memory.  
+
+### `X-Ray_Alpha-q4_k_s.gguf`  
+- Smallest **Q4_K** variant, using less memory at the cost of accuracy.  
+- Best for **very low-memory setups**.  
+
+### `X-Ray_Alpha-q6_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q6_K** .  
+
+### `X-Ray_Alpha-q8_0.gguf`  
+- Fully **Q8** quantized model for better accuracy.  
+- Requires **more memory** but offers higher precision.  
+
+### `X-Ray_Alpha-iq3_xs.gguf`  
+- **IQ3_XS** quantization, optimized for **extreme memory efficiency**.  
+- Best for **ultra-low-memory devices**.  
+
+### `X-Ray_Alpha-iq3_m.gguf`  
+- **IQ3_M** quantization, offering a **medium block size** for better accuracy.  
+- Suitable for **low-memory devices**.  
+
+### `X-Ray_Alpha-q4_0.gguf`  
+- Pure **Q4_0** quantization, optimized for **ARM devices**.  
+- Best for **low-memory environments**.
+- Prefer IQ4_NL for better accuracy.
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+❤ **Please click "Like" if you find this useful!**  
+Help me test my **AI-Powered Network Monitor Assistant** with **quantum-ready security checks**:  
+👉 [Quantum Network Monitor](https://readyforquantum.com)  
+
+💬 **How to test**:  
+1. Click the **chat icon** (bottom right on any page)  
+2. Choose an **AI assistant type**:  
+   - `TurboLLM` (GPT-4-mini)  
+   - `FreeLLM` (Open-source)  
+   - `TestLLM` (Experimental CPU-only)  
+
+### **What I’m Testing**  
+I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  
+- **Function calling** against live network services  
+- **How small can a model go** while still handling:  
+  - Automated **Nmap scans**  
+  - **Quantum-readiness checks**  
+  - **Metasploit integration**  
+
+🟡 **TestLLM** – Current experimental model (llama.cpp on 6 CPU threads):  
+- ✅ **Zero-configuration setup**  
+- ⏳ 30s load time (slow inference but **no API costs**)  
+- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  
+
+### **Other Assistants**  
+🟢 **TurboLLM** – Uses **gpt-4-mini** for:  
+- **Real-time network diagnostics**  
+- **Automated penetration testing** (Nmap/Metasploit)  
+- 🔑 Get more tokens by [downloading our Quantum Network Monitor Agent](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  
+
+🔵 **HugLLM** – Open-source models (≈8B params):  
+- **2x more tokens** than TurboLLM  
+- **AI-powered log analysis**  
+- 🌐 Runs on Hugging Face Inference API  
+
+### 💡 **Example AI Commands to Test**:  
+1. `"Give me info on my websites SSL certificate"`  
+2. `"Check if my server is using quantum safe encyption for communication"`  
+3. `"Run a quick Nmap vulnerability test"`
+4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution!
+
+### Final word
+I fund the servers to create the models files, run the Quantum Network Monitor Service and Pay for Inference from Novita and OpenAI all from my own pocket. All of the code for creating the models and the work I have done with Quantum Network Monitor is [open source](https://github.com/Mungert69). Feel free to use what you find useful. Please support my work and consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) .
+This will help me pay for the services and increase the token limits for everyone.
+
+Thank you :)  
+
+
+
+<div align="center">
+  <b style="font-size: 40px;">X-Ray_Alpha</b>
+
+
+</div>
+
+
+<img src="https://huggingface.co/SicariusSicariiStuff/X-Ray_Alpha/resolve/main/Images/X-Ray_Alpha.png" alt="X-Ray_Alpha" style="width: 30%; min-width: 450px; display: block; margin: auto;">
+
+
+---
+
+<div style="display: flex; justify-content: center; align-items: center;">
+  <a href="https://huggingface.co/SicariusSicariiStuff/X-Ray_Alpha#tldr"
+     style="color: #800080; font-weight: bold; font-size: 28px; text-decoration: none; margin: 0 20px;">
+    Click here
+     for TL;DR
+  </a>
+  <a href="https://huggingface.co/SicariusSicariiStuff/X-Ray_Alpha#why-is-this-important"
+     style="color: #1E90FF; font-weight: bold; font-size: 28px; text-decoration: none; margin: 0 20px;">
+        Why it's
+    important
+  </a>
+  <a href="https://huggingface.co/SicariusSicariiStuff/X-Ray_Alpha#how-can-you-help"
+     style="color: #32CD32; font-weight: bold; font-size: 28px; text-decoration: none; margin: 0 20px;">
+    How can YOU
+    help?
+  </a>
+  <a href="https://huggingface.co/SicariusSicariiStuff/X-Ray_Alpha#how-to-run-it"
+     style="color: #E31515; font-weight: bold; font-size: 28px; text-decoration: none; margin: 0 20px;">
+    How to
+    RUN IT
+  </a>
+</div>
+
+
+
+---
+
+This is a pre-alpha proof-of-concept of **a real fully uncensored vision model**.
+
+Why do I say **"real"**? The few vision models we got (qwen, llama 3.2) were "censored," and their fine-tunes were made only to the **text portion** of the model, as training a vision model is a serious pain.
+
+The only actually trained and uncensored vision model I am aware of is [ToriiGate](https://huggingface.co/Minthy/ToriiGate-v0.4-7B); the rest of the vision models are just the stock vision + a fine-tuned LLM.
+
+# Does this even work?
+
+<h2 style="color: green; font-weight: bold; font-size: 80px; text-align: center;">YES!</h2>
+
+---
+
+# Why is this Important?
+
+Having a **fully compliant** vision model is a critical step toward democratizing vision capabilities for various tasks, especially **image tagging**. This is a critical step in both making LORAs for image diffusion models, and for mass tagging images to pretrain a diffusion model.
+
+In other words, having a fully compliant and accurate vision model will allow the open source community to easily train both loras and even pretrain image diffusion models.
+
+Another important task can be content moderation and classification, in various use cases there might not be black and white, where some content that might be considered NSFW by corporations, is allowed, while other content is not, there's nuance. Today's vision models **do not let the users decide**, as they will straight up **refuse** to inference any content that Google \ Some other corporations decided is not to their liking, and therefore these stock models are useless in a lot of cases.
+
+What if someone wants to classify art that includes nudity? Having a naked statue over 1,000 years old displayed in the middle of a city, in a museum, or at the city square is perfectly acceptable, however, a stock vision model will straight up refuse to inference something like that.
+
+It's like in many "sensitive" topics that LLMs will straight up **refuse to answer**, while the content is **publicly available on Wikipedia**. This is an attitude of **cynical patronism**, I say cynical because corporations **take private data to train their models**, and it is "perfectly fine", yet- they serve as the **arbitrators of morality** and indirectly preach to us from a position of a suggested moral superiority. This **gatekeeping hurts innovation badly**, with vision models **especially so**, as the task of **tagging cannot be done by a single person at scale**, but a corporation can.
+
+# How can YOU help?
+
+This is sort of **"Pre-Alpha"**, a proof of concept, I did **A LOT** of shortcuts and "hacking" to make this work, and I would greatly appreciate some help to make it into an accurate and powerful open tool. I am not asking for money, but well-tagged data. I will take the burden and costs of the compute on myself, but I **cannot do tagging** at a large scale by myself.
+
+## Bottom line, I need a lot of well-tagged, diverse data
+
+So:
+
+- If you have well-tagged images
+- If you have a link to a well-tagged image dataset
+- If you can, and willing to do image tagging
+
+Then please send an email with [DATASET] in the title to:
+
+```
+spamthesicarius@gmail.com
+```
+
+As you probably figured by the email address name, this is not my main email, and I expect it to be spammed with junk, so **please use the [DATASET] tag** so I can more easily find the emails of **the good people** who are actually trying to help.
+
+## Please see this dataset repo if you want to help:
+
+[X-Ray_Community_Tagging](https://huggingface.co/datasets/SicariusSicariiStuff/X-Ray_Community_Tagging)
+
+
+Also, if you don't want to upload it to the repo (although it's encouraged, and you can protect it with a password for privacy), you can still help by linking a google drive
+or attach the images with the corrected output via the provided email.
+
+Let's make this happen. We can do it!
+
+---
+
+### TL;DR
+- **Fully uncensored and trained** there's no moderation in the vision model, I actually trained it.
+- **The 2nd uncensored vision model in the world**, ToriiGate being the first as far as I know, and this one is the second.
+- **In-depth descriptions** very detailed, long descriptions.
+- The text portion is **somewhat uncensored** as well, I didn't want to butcher and fry it too much, so it remain "smart".
+- **NOT perfect** This is a POC that shows that the task can even be done, a lot more work is needed.
+- **Good Roleplay & Writing** I used a massive corpus of high quality human (**~60%**) and synthetic data.
+
+
+---
+
+# How to run it:
+
+
+## VRAM needed for FP16: 15.9 GB
+
+[Run inference with this](https://github.com/SicariusSicariiStuff/X-Ray_Vision)
+
+# This is a pre-alpha POC (Proof Of Concept)
+
+## Instructions:
+clone:
+```
+git clone https://github.com/SicariusSicariiStuff/X-Ray_Vision.git
+cd X-Ray_Vision/
+```
+
+Settings up venv, (tested for python 3.11, probably works with 3.10)
+```
+python3.11 -m venv env
+source env/bin/activate
+```
+
+Install dependencies
+```
+pip install git+https://github.com/huggingface/transformers@v4.49.0-Gemma-3
+pip install torch
+pip install pillow
+pip install accelerate
+```
+
+# Running inference
+
+Usage:
+```
+python xRay-Vision.py /path/to/model/ /dir/with/images/
+```
+The output will print to the console, and export the results into a dir named after your image dir with the suffix "_TXT"
+
+So if you run:
+```
+python xRay-Vision.py /some_path/x-Ray_model/ /home/images/weird_cats/
+```
+The results will be exported to:
+```
+/home/images/weird_cats_TXT/
+```
+
+---
+
+<h2 style="color: green; font-weight: bold; font-size: 65px; text-align: center;">Your support = more models</h2>
+<a href="https://ko-fi.com/sicarius" style="color: pink; font-weight: bold; font-size: 48px; text-decoration: none; display: block; text-align: center;">My Ko-fi page (Click here)</a>
+
+---
+
+
+## Citation Information
+
+```
+@llm{X-Ray_Alpha,
+  author = {SicariusSicariiStuff},
+  title = {X-Ray_Alpha},
+  year = {2025},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/SicariusSicariiStuff/X-Ray_Alpha}
+}
+```
+
+---
+
+## Other stuff
+- [X-Ray_Vision](https://github.com/SicariusSicariiStuff/X-Ray_Vision) Easy stand-alone bulk vision inference at scale (inference a folder of images).
+- [SLOP_Detector](https://github.com/SicariusSicariiStuff/SLOP_Detector) Nuke GPTisms, with SLOP detector.
+- [LLAMA-3_8B_Unaligned](https://huggingface.co/SicariusSicariiStuff/LLAMA-3_8B_Unaligned) The grand project that started it all.
+- [Blog and updates (Archived)](https://huggingface.co/SicariusSicariiStuff/Blog_And_Updates) Some updates, some rambles, sort of a mix between a diary and a blog.

X-Ray_Alpha-bf16-q4_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0b9956a4d055edf6c2ca470914e89662c6fd7f2add6f92da5d37d4fe96825c
+size 3281762496

X-Ray_Alpha-bf16-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c5344a50e170f9db58d44568986c7c5c1e2021e19e141ef0a680d6507dbc728
+size 3982608576

X-Ray_Alpha-bf16-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81222a0a925f0aeb2d9a76198d53d6bf54daebafc0ce5cff6bb6b36c9692e14
+size 4759701408

X-Ray_Alpha-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb61449ce3afa7b6a27ea22cf14f1bf883ca0764929fde4d4e08ff3c736711e3
+size 7767803808

X-Ray_Alpha-f16-q4_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88dc25698bc117cee35637e4b2f243fb1769c68024c77a1cb9d5df66bb383d84
+size 3281762496

X-Ray_Alpha-f16-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c24666a562dcc1b411f0321dd6e2a62b62f366f2f3cb20a293c70c25ef8024
+size 3982608576

X-Ray_Alpha-f16-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ca0975f59d7acdd760cc86369b3ce6b4ef5ee008fe69ddd48f4a3d3d900281
+size 4759701408

X-Ray_Alpha-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a9490055efdd0e0250cfa4006e75127c1aeb4f7aca040162879d876b2fecb8e
+size 1299513536

X-Ray_Alpha-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5d12deecd7ebdfa3a89673a8cc9852d576167e2a916d7753bbe70d28e92091
+size 1251467456

X-Ray_Alpha-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4542bdbbd2d992277ea2f78d67f3d8e8078f1952947d0d30ed555627b7bd76dc
+size 1669259456

X-Ray_Alpha-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30869f04d61609413f04cd8a093a734db0cbd69d6b4532460410e4ecd87b27b
+size 1605198016

X-Ray_Alpha-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5f2746fb19b1e8590f5592b643eb5a8130573ad9f1c085b314ff23d365d1ba
+size 1449222336

X-Ray_Alpha-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d38276174f85a6131c434c86ddd76521238bb199156d260bdbbb024b140c4cf9
+size 1379590336

X-Ray_Alpha-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a082d8495db5c326ce3f76060b9d2049b50b5cfbfe70c554ea724bdcda59d6
+size 1897652416

X-Ray_Alpha-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19a155e415dd5ed30389be2ae82a55088ad3e48fde020e1c26e869e0108aa50
+size 1848213696

X-Ray_Alpha-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ed2f9a79dc35536e78a3b3baebbf92421f787cb4cf8a18712c16169de8caa98
+size 1774239936

X-Ray_Alpha-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94cd3cad7e82e4687b8a76a44076a7e543497cd6764f6d6f2c54da741985b75b
+size 1689452736

X-Ray_Alpha-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f283bd703b2f47888f07de82b9f22e4d2b508795caf5549b4a5abcf7b1d239
+size 2363512256

X-Ray_Alpha-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf3ebf41c4ce08ebdb447c496cbdda336ebbf06fe74c2a1cfe1a697d029b675
+size 2263242176

X-Ray_Alpha-mmproj-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2acad08c28370356299cbb25c9934d6c1da2a88ce358ccf5eda3ea65b71f8cc
+size 851251104

X-Ray_Alpha-mmproj-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8293523d84e169c1543693cd1487b8325fd36f581c19cf383afbe69a0e18abf
+size 1679290272

X-Ray_Alpha-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51307493c4d7291b9a9ef28baa5a9c0415e50405102c5efacbc7dd709fdba8dc
+size 1546911936

X-Ray_Alpha-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faca34df23d52a940a052588bb4fe66848fa2a4d5ac801d4d2da0a226517b092
+size 2009309376

X-Ray_Alpha-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c33010f2ef888f27f93740689742d5cfe77f35e990ad0a7b7bd616b2dbb461
+size 1848213696

X-Ray_Alpha-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85faaab0e4ff083d4e74e54ff6843545e06c2d21e9bbec5a9ccb99ac0920867b
+size 2190454976

X-Ray_Alpha-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96bd382f2fd612cde5ea4bd2a37b1bf4c66eaf73da3ab623afab0dfcc31687f9
+size 2432948416

X-Ray_Alpha-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7ef54a432221353063be27a2423e7a91e1db9aa59f3844478fbe8febeb54c3
+size 2489894336

X-Ray_Alpha-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953157d760784dd635308471245bc5c3894e42f5f06db86d310f72dcb2dcf667
+size 2377930176

X-Ray_Alpha-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577b2e3dbad3540ee146055fe3d34f231cfe8fd0afbdc246b1732268e6acf273
+size 2675441856

X-Ray_Alpha-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3751e14a8c5094b440ae45d4fa395477ecec23c6a055dd38a833512f899ee23d
+size 2917935296

X-Ray_Alpha-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c0d5fda719275d696374449d0ccd1a47b33c71f57756a2f140f84bfa439a34f
+size 2829698496

X-Ray_Alpha-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30da11dc41e6c12f8063b1f33befec82077aae6077082c15c919b73a94abab32
+size 2764592576

X-Ray_Alpha-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6336ea0807789520c7c5ebe61405f184d436fd44670dae716c37739511fe9952
+size 3190740416

X-Ray_Alpha-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d216e65c376d57415b10a5f5348c49b969c9f04d208edd854e22760701e417cf
+size 4130402208

X-Ray_Alpha-tq1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e283a331da548e45b79a93c565d94931011dca492069bc522d4b26394d559023
+size 1235473856

X-Ray_Alpha-tq2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b9b774fbcc5464d538e159ba5257acc1a2178d5e34619e438f891fd3c62918
+size 1385878976

X-Ray_Alpha.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1160efcee17fceac7481112e617828856c13a8584930a3897b3860e2496f2d7b
+size 3419868