Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,67 @@
+*.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
+DeepMedix-R1-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-f32.mmproj filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-f16.mmproj filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-q8_0.mmproj filter=lfs diff=lfs merge=lfs -text
+DeepMedix-R1-bf16.mmproj filter=lfs diff=lfs merge=lfs -text

DeepMedix-R1-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e53002b08eb33a466aa2dd4ab163b76420659ba76e96b5db4de580dce69597b4
+size 15237853184

DeepMedix-R1-bf16.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5651afd1de8bbc429e4f97a15a1190322b26d831ba881e16b1b6b2f295b83e
+size 1357173408

DeepMedix-R1-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed229630b608edb4666ae924890ad6f95449315512aefff508ad04f14aca21d7
+size 11287998464

DeepMedix-R1-f16.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e35a75d3472b4858d44d905f38dd86b1e9bd407bffa4a983cdb322f5ae9937
+size 1354162848

DeepMedix-R1-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0702eca3eb9719e4ac64e052b20af43eff7a39c9e8dc12a20ff07ec2be61de
+size 11287998464

DeepMedix-R1-f32.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b208454e38a68add118b565d795dfaec489c1992db36fb749fe5ac2c04b37bde
+size 2706231968

DeepMedix-R1-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfca0910d5b2ed1db14751bcbf920b3b18fd40efae28add535a21fc785deafc9
+size 4560416

DeepMedix-R1-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd85c97ed6a4ec0f8034c4b51cfedf60a0960b35e5d94bdc4760bd9499b2214b
+size 2571997504

DeepMedix-R1-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf912d9d091732b5ba0946486f02177f222de1eca59355be021039f4fc09c18
+size 2278224192

DeepMedix-R1-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fab4982517117823eb0b4755ab560d8b8052f696212df8caa7298229bd8f7c0
+size 3041730880

DeepMedix-R1-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9596421244237aee1cfbc7622db63268ca314a1ce36cfc7520712ec4f9afa53
+size 2915574080

DeepMedix-R1-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08ce348b9dabcc289a1f98394e88d40c529e25f9ef76fad3e89fc4c6dada38c
+size 2839335232

DeepMedix-R1-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c2307ae5740ee7dc67af04af2927f0e29a139a1a440053eff897d9fa8b65727
+size 2652107072

DeepMedix-R1-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c45e5d5337d535d9c8c8edf849b67443778e11bc3ca78ae2b0f0e414875f59
+size 3924455744

DeepMedix-R1-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963bf94382932f8e846649b9da7ef9c93da149fd3f53134a901af44ca13e03b4
+size 3594813760

DeepMedix-R1-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b59b912b5780fc779abdb6a2ffbfff380f55a48c04b6238ea9f319cb8b23415
+size 3524567360

DeepMedix-R1-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1075d31e83f3f477810597f1cf3c98e526dc53d73380f8df037c0b075727b2bc
+size 4297306432

DeepMedix-R1-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3326eae5693154baf9fc805fc282b77c29429c319620c77a8dd422b40448166f
+size 4376011072

DeepMedix-R1-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b19c45e18036cfcac5ddb4ddd32be9dddabd949d6c02a991b8e64f69844d82
+size 3119345984

DeepMedix-R1-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c86dd4788d7ec6e2782b778da8844b4914305f21aaa5d25b9460c9d58d2a259
+size 2983096640

DeepMedix-R1-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd397b7bc9f94c9bf1824161df7ac665049ffa0c7ba9a10f1ea430ef8e3e7b1
+size 4003504448

DeepMedix-R1-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe10a04035436adf2d8405f1bbd326c2a3d7d0982ee38375f06367776c058e0
+size 3858739520

DeepMedix-R1-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20f747fc62482993874794036bb0a354a1a1c24bd6112d1b59e3c682835077e
+size 4835881280

DeepMedix-R1-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d9bbb5b4572fcdaf905b3eed64b2d813d9bdc4d15c235786adfbb909c300a0
+size 4834963776

DeepMedix-R1-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2242b6ae311de10bd1cd0e51e2bc6c472251474914ee5934f28be13f114a4bb
+size 5041631552

DeepMedix-R1-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7988bd5fc4bfbfb70fbb90fc9fa0493b61fd61926c261696f8f5b14abedae3b6
+size 4634059072

DeepMedix-R1-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6c08ac9ba4f5bdc4a27889946e4b55ce32c7f6b40c7f84378b7783765c5713
+size 5651542336

DeepMedix-R1-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f68a8d83e56d78c7ba3ad03e549d23baacdbf9640a2e240353f8a15533391aa
+size 6059372864

DeepMedix-R1-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c420ba0f6103f46553524407847b9dc8e651614d9fb2ae9f9a57750b27f3c8ef
+size 5791433024

DeepMedix-R1-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978bd627a6b5d0ba995b468baa3974b9a38a64e236001e06d2f1ba08ac26a9d7
+size 6518182208

DeepMedix-R1-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf9770d75cbfd8d1acf629303087bbb4ae8ceeff3b1f1217a174e1b5e542a21
+size 8098525184

DeepMedix-R1-q8_0.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10805ca2677b6c4e8254d821d392262cdbce8d11ea8e4c48fddb083167fd1d8c
+size 856130208

README.md

@@ -0,0 +1,168 @@
+---
+license: apache-2.0
+---
+
+# <span style="color: #7FFF7F;">DeepMedix-R1 GGUF Models</span>
+
+
+## <span style="color: #7F7FFF;">Model Generation Details</span>
+
+This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`fb15d649`](https://github.com/ggerganov/llama.cpp/commit/fb15d649ed14ab447eeab911e0c9d21e35fb243e).
+
+
+
+
+
+---
+
+## <span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>
+
+I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.
+
+In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here:  
+👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py)
+
+While this does increase model file size, it significantly improves precision for a given quantization level.
+
+### **I'd love your feedback—have you tried this? How does it perform for you?**
+
+
+
+
+---
+
+<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
+  Click here to get info on choosing the right GGUF model format
+</a>
+
+---
+
+
+
+<!--Begin Original Model Card-->
+
+
+Model Usage:
+
+~~~
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
+from qwen_vl_utils import process_vision_info
+
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    model_path,
+    torch_dtype=torch.bfloat16,
+    attn_implementation="flash_attention_2",
+    device_map="auto",
+)
+processor = AutoProcessor.from_pretrained(model_path, max_pixels=262144)
+
+
+reason_prompt = r"You FIRST think about the reasoning process as an internal monologue and then provide the final answer. The reasoning process MUST BE enclosed within <think> </think> tags. During this reasoning process, prioritize analyzing the local regions of the image by leveraging the bounding box coordinates in the format [x_min, y_min, x_max, y_max]. The final answer MUST BE put in \boxed{}. An example is like: <think> reasoning process 1 with [x_min1, y_min1, x_max1, y_max1]; reasoning process 2 with [x_min2, y_min2, x_max2, y_max2] </think>. The answer is: \boxed{answer}."
+
+def get_label(images, content1):
+    content_list = []
+    for image_url in images:
+        content_list.append({
+            "type": "image",
+            "image": image_url,
+        })
+    if mode == 'think':
+        content_list.append({"type": "text",
+                             "text": content1 + '\n' + reason_prompt + '\n'})
+    else:
+        content_list.append({"type": "text",
+                             "text": content1})
+    messages = [
+        {
+            "role": "user",
+            "content": content_list
+        }
+    ]
+
+    # Preparation for inference
+    text = processor.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+    # print(text)
+    image_inputs, video_inputs = process_vision_info(messages)
+    inputs = processor(
+        text=[text],
+        images=image_inputs,
+        videos=video_inputs,
+        padding=True,
+        return_tensors="pt",
+    )
+    inputs = inputs.to("cuda")
+
+    # Inference: Generation of the output
+    generated_ids = model.generate(**inputs, max_new_tokens=4096, do_sample=True, temperature=0.6)
+    generated_ids_trimmed = [
+        out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+    ]
+    output_text = processor.batch_decode(
+        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    )
+    # print(output_text)
+    # print(output_text[0])
+    return output_text[0]
+
+~~~
+
+<!--End Original Model Card-->
+
+---
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+
+Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:  
+
+👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  
+
+
+The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)
+
+💬 **How to test**:  
+ Choose an **AI assistant type**:  
+   - `TurboLLM` (GPT-4.1-mini)  
+   - `HugLLM` (Hugginface Open-source models)  
+   - `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 security scans**  
+  - **Quantum-readiness checks**  
+  - **Network Monitoring tasks**  
+
+🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):  
+- ✅ **Zero-configuration setup**  
+- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.
+- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  
+
+### **Other Assistants**  
+🟢 **TurboLLM** – Uses **gpt-4.1-mini** :
+- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. 
+- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
+- **Real-time network diagnostics and monitoring**
+- **Security Audits**
+- **Penetration testing** (Nmap/Metasploit)  
+
+🔵 **HugLLM** – Latest Open-source models:  
+- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
+
+### 💡 **Example commands you could 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 comprehensive security audit on my server"`
+4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution!
+
+### Final Word
+
+I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
+
+If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
+
+I'm also open to job opportunities or sponsorship.
+
+Thank you! 😊