Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,77 @@
+*.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
+DiffuCoder-7B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text
+DiffuCoder-7B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text

DiffuCoder-7B-Instruct-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e33c702f1ce381f81af8c3e77a1af62d1366725ae679d28473454d99ae45dc5
+size 15237853600

DiffuCoder-7B-Instruct-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a1aed9016e264f5689aa227d850a18eed27a62fad63ce083d8f2863e1aae58
+size 11287998880

DiffuCoder-7B-Instruct-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f2de9946498281ec20856770d7b67dde29e28cc74aff9300202d61e156a55d
+size 11287998880

DiffuCoder-7B-Instruct-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c231bbd50fd7f960b833a548c8acc8b688d1a9be8480671d9c42c53c49b2ddf3
+size 3039122144

DiffuCoder-7B-Instruct-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0385a02bed30de2a973a675b9c807348523dea9f4a59597205809dcfbae85ca5
+size 2912965344

DiffuCoder-7B-Instruct-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b5fcf060c24e197889aadc6b920d0236f6bf4938c518fc4397a170c719a672
+size 2839335648

DiffuCoder-7B-Instruct-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee7212d2da7b2904c12fd2c85bf70180dbea64b15ba8168c702ff0f2c7fa768
+size 2650903264

DiffuCoder-7B-Instruct-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9352012f28ae3b712768f09e7b5f7f426a44354dcc30e938ccf9bea0909be78d
+size 3779691232

DiffuCoder-7B-Instruct-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95bec9d36c4963cdd531ef3e6769551c3d1c00a46a92530a20e7614d4ca15eb9
+size 3779691232

DiffuCoder-7B-Instruct-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ca0b8178230e88e3fa2f32d8d371d4f0cb9538d758e8878e703ba627a86adb
+size 3450049248

DiffuCoder-7B-Instruct-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241e761caf9faba4974e1bf24373cec4b59ac00d5a1623a0986a6bc7596b23ed
+size 3379802848

DiffuCoder-7B-Instruct-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dab52f7924d97eafb9e9c78fd33b79eddf8b0e30a5a3bb7d2572bf102719d8b
+size 4437813984

DiffuCoder-7B-Instruct-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8735c4372b0897d102a4db858a7e7b044ec4c1a96ae823b98e54b80037ccf4b
+size 4218473184

DiffuCoder-7B-Instruct-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c226cdaf9e06ce1512b537788791b01022af8bdd2a8580439dddab7ed4dff63
+size 3264111328

DiffuCoder-7B-Instruct-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6441f707e7c2ff11d402ba0b89b21a1ea569029a60f8ac930cc14f75612f73db
+size 3119346400

DiffuCoder-7B-Instruct-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7071878caeef9fb2690312c388b4ebf4dc211b68313c411991722a22468a98c4
+size 4003504864

DiffuCoder-7B-Instruct-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8b74174122d7e9d8e60a7dc18856b27d94b3f2b82a13274bc453bbbc0c0adad
+size 3858739936

DiffuCoder-7B-Instruct-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0b76eb6b0d46c507d939debc19809f920601ce752dc16b9e545accb0231dbe
+size 4290884320

DiffuCoder-7B-Instruct-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab12b84836a6afcf7af0673b0f67a4b009620f43fa721280263fca42c2a4bdbb
+size 4766839520

DiffuCoder-7B-Instruct-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c75e79fae99bdc4fce7b789a7ac851c79c163fe62fdb756ec2ddb313be7f64
+size 4777648864

DiffuCoder-7B-Instruct-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a17e07bf928c272b08a69e6271b004457918fafde97688fbda9208d12503396
+size 4634059488

DiffuCoder-7B-Instruct-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b57ae8662aa468418e4b164a7cf928ac0273f415822bac078e36dd162b50dc
+size 5242794720

DiffuCoder-7B-Instruct-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0faf2541ac881cb64c45022a7fa56ad4eb868987014ec8078dd0cfbb356ad83d
+size 5718749920

DiffuCoder-7B-Instruct-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64893fa62db549740fdae58a7313f16e6389de32f04ed8cbdcf8c2f56dafd0bf
+size 5527450336

DiffuCoder-7B-Instruct-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523f5f2caf522ee2bcd4314bf5f23292df94d593333e031478159308c14fa856
+size 5453361888

DiffuCoder-7B-Instruct-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10128dbc527fd286d60188d123abed2bc64e9e33bbf9eff42183d6cc1dc01dac
+size 6254199520

DiffuCoder-7B-Instruct-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3169e10ea56b81416e70db844035aad2b80504dc5d4c7aa6400b9373edf636d9
+size 8098525600

DiffuCoder-7B-Instruct.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:369e0ed165ad76e3f14747e943b1fb460533a7575f229a0cc6faa8fbc5c230a2
+size 4536712

README.md

@@ -0,0 +1,170 @@
+---
+base_model:
+- apple/DiffuCoder-7B-Base
+tags:
+- code
+- text-diffusion-model
+- diffusion large language model
+license: unknown
+---
+
+# <span style="color: #7FFF7F;">DiffuCoder-7B-Instruct 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 [`21c02174`](https://github.com/ggerganov/llama.cpp/commit/21c021745d781edf9c44b4972ef6cbbf53b0ecff).
+
+
+
+
+
+---
+
+## <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-->
+
+### DiffuCoder-7B-Instruct 
+
+The DiffuCoder-7B-Instruct model builds on the DiffuCoder-7B-Base checkpoint with instruction-tuning to better follow code-related prompts.
+
+- Training recipe: with a newly introduced pad token, we train this model with fixed length conditionally on [OpenCoder-SFT](https://huggingface.co/datasets/OpenCoder-LLM/opc-sft-stage2) data for 5 epochs.
+
+- Benchmarks: Demonstrates stronger instruction-following capabilities than the Base model.
+
+
+#### More details and usage examples:
+
+- Paper: [DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation](https://arxiv.org/abs/2506.20639)
+
+- GitHub: https://github.com/apple/ml-diffucoder
+
+```
+import torch
+from transformers import AutoModel, AutoTokenizer
+
+model_path = "apple/DiffuCoder-7B-Instruct"
+model = AutoModel.from_pretrained(model_path, torch_dtype=torch.bfloat16, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+model = model.to("cuda").eval()
+
+query = "Write a function to find the shared elements from the given two lists."
+prompt = f"""<|im_start|>system
+You are a helpful assistant.<|im_end|>
+<|im_start|>user
+{query.strip()}
+<|im_end|>
+<|im_start|>assistant
+""" ## following the template of qwen; you can also use apply_chat_template function
+
+TOKEN_PER_STEP = 1 # diffusion timesteps * TOKEN_PER_STEP = total new tokens
+
+inputs = tokenizer(prompt, return_tensors="pt")
+input_ids = inputs.input_ids.to(device="cuda")
+attention_mask = inputs.attention_mask.to(device="cuda")
+
+output = model.diffusion_generate(
+    input_ids,
+    attention_mask=attention_mask,
+    max_new_tokens=256,
+    output_history=True,
+    return_dict_in_generate=True,
+    steps=256//TOKEN_PER_STEP,
+    temperature=0.3,
+    top_p=0.95,
+    alg="entropy",
+    alg_temp=0.,
+)
+generations = [
+    tokenizer.decode(g[len(p) :].tolist())
+    for p, g in zip(input_ids, output.sequences)
+]
+
+print(generations[0].split('<|dlm_pad|>')[0])
+```
+
+#### Acknowledgement
+To power this HuggingFace model release, we reuse [Dream](https://huggingface.co/Dream-org/Dream-v0-Base-7B)'s modeling architecture and generation utils.
+
+
+<!--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! 😊