Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,60 @@
+*.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
+II-Search-4B-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+II-Search-4B-bf16.gguf filter=lfs diff=lfs merge=lfs -text

II-Search-4B-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab41d146a03d98d6b15d8b32224140262a40c4997be851b2424b2f65baaa619e
+size 8829197024

II-Search-4B-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf046181cd0583dd2ac52f5861b19968a3d4e55ac311a4704467d1f7c0c1a58
+size 6705830624

II-Search-4B-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd424ec838b82dddab70c869e3735eca087ae20f81d6be5705c9f0722027ad0
+size 6705830624

II-Search-4B-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a2f473076879334e6776d413b8df500b7c5e95b1777ddc0a8de541f1bb974b
+size 3872672

II-Search-4B-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc4c3c793d52dc57654023658315a9a84e875c6386f5356c9915ef0b3e108db
+size 1823153184

II-Search-4B-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a713bb3f953d2ec45dff2e7bd5bec10ad44c84fa6d21aa7ae6210071fb6ffb3
+size 1758927904

II-Search-4B-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44c295ebc2c99eaeee6b955a1b3d7046dbf5ac0950533ec34599b746f4ad0bb
+size 1713585184

II-Search-4B-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b02cbb6634959f3c433ef40036a1f5a6b414b269da66b157b7a504aa8325d048
+size 1609341984

II-Search-4B-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57139b55de625dbb7eb2ab416d69f3c2adad2d20172e7a56ae39be8bf7ac19b5
+size 2322102304

II-Search-4B-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81a17341d98b76022600dd16dedb2c42103a429c3e637fe4099b6957e6a5e4d9
+size 2322102304

II-Search-4B-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84c3ab6588edf157fadb94bd2a6d556aef3f40207fd1ab2fdb4a40d1c0e379b
+size 2143270944

II-Search-4B-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62fa7b7750219c3dcf7797688b056136a4f6269bda0206d04b97a65dc6d8564
+size 2092767264

II-Search-4B-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9c022728d9b3454539b41898f87895dd6be3b2a48906b116ea840c4326b41b
+size 2499853344

II-Search-4B-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b6c797afb0a56656aa67ec3d78b04c8393f65c67e18ea12c67b7e90ecf6f49e
+size 2589816864

II-Search-4B-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3fb870dc15aae847cfb1037c44b3288de2fd9a9f771d41e197dd01e9d6e41e
+size 1858952224

II-Search-4B-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a191c1ab6c64dce7e353cda2af80acec344639137992b0da2cb1d7261b94537
+size 1761713184

II-Search-4B-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c4510faaa147491cd43f8a1414688ec6eedf9f44059cf9c4fd19434dadd736
+size 2378627104

II-Search-4B-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c5e2b98383b9ad804accb6fd5d2ea35215071ec9c15d3844e6709234705072
+size 2275310624

II-Search-4B-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:877e960355e7ed4a0ee6b632164401d33295b66a7d3e4ae0c649208854c961c9
+size 2877013024

II-Search-4B-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fac58dfe6e537b461ed3976142e511711bc4aa53170cfa819171cfd4c4e9596
+size 2812378144

II-Search-4B-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d8c99b74054abd248a59b44ca1a5fa7226c22d0c4550c070f836ede1941405
+size 2985987104

II-Search-4B-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2e00e74c97066df3153f6453b921ae858895c86fcde4040d98109b525786612
+size 2726623264

II-Search-4B-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:547ccedf6fc0dd0cd9978c66f457fdffc9dc9c192a315f4fb34a178e1aca2fda
+size 3331177504

II-Search-4B-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:537fd2814e393a22ca79a37477266390c37458345fb368f7611e86f5b18c7972
+size 3558259744

II-Search-4B-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebbab20f5fc33ccd34e729d243aaa317f759297014136158f57558143931cfbe
+size 4693670624

README.md

@@ -0,0 +1,238 @@
+---
+base_model:
+- Qwen/Qwen3-4B
+pipeline_tag: text-generation
+library_name: transformers
+license: apache-2.0
+---
+
+# <span style="color: #7FFF7F;">II-Search-4B 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 [`cd6983d5`](https://github.com/ggerganov/llama.cpp/commit/cd6983d56d2cce94ecb86bb114ae8379a609073c).
+
+
+
+
+
+---
+
+## <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-->
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63466107f7bd6326925fc770/b6xfld0bUDDAQIFvMCapD.png)
+
+# II-Search-4B
+
+
+
+<aside>
+
+A 4B parameter language model specialized in information seeking, multi-hop reasoning, and web-integrated search, achieving state-of-the-art performance among models of similar size.
+
+</aside>
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63466107f7bd6326925fc770/rUpsG4-X9ZdO6JVEp6xVO.png)
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63466107f7bd6326925fc770/83kNxbdWU8mk8lqLZ9Gnb.png)
+
+## Model Description
+
+II-Search-4B is a 4B parameter language model based on Qwen3-4B, fine-tuned specifically for information seeking tasks and web-integrated reasoning. It excels at complex multi-hop information retrieval, fact verification, and comprehensive report generation.
+
+### Key Features
+
+- Enhanced tool usage for web search and webpage visits
+- Multi-hop reasoning capabilities with sophisticated planning
+- Verified information retrieval with cross-checking
+- Strong performance on factual QA benchmarks
+- Comprehensive report generation for research queries
+
+## Training Methodology
+
+Our training process consisted of three key phases:
+
+### Phase 1: Tool Call Ability Stimulation
+
+We used a distillation approach from larger models (Qwen3-235B) to generate reasoning paths with function calling on multi-hop datasets. This established the base capabilities for tool use.
+
+### Phase 2: Reasoning Improvement
+
+We addressed initial limitations by:
+
+- Creating synthetic problems requiring more reasoning turns, inspired by Random Walk algorithm
+- Improving reasoning thought patterns for more efficient and cleaner reasoning paths
+
+### Phase 3: Rejection Sampling & Report Generation
+
+We applied:
+
+- Filtering to keep only high-quality reasoning traces (correct answers with proper reasoning)
+- STORM-inspired techniques to enhance comprehensive report generation
+
+### Phase 4: Reinforcement Learning
+
+We trained the model using reinforcement learning
+- Used dataset: [dgslibisey/MuSiQue](https://huggingface.co/datasets/dgslibisey/MuSiQue)
+- Incorporated our in-house search database (containing Wiki data, Fineweb data, and ArXiv data)
+
+## Performance
+
+| **Benchmark** | **Qwen3-4B** | **Jan-4B** | **WebSailor-3B** | **II-Search-4B** |
+| --- | --- | --- | --- | --- |
+| OpenAI/SimpleQA | 76.8 | 80.1 | 81.8 | 91.8 |
+| Google/Frames | 30.7 | 24.8 | 34.0 | 67.5 |
+| Seal_0 | 6.31 | 2.7 | 1.8 | 22.5 |
+
+### Tool Usage Comparison
+
+**Simple QA (SerpDev)**
+
+|  | **Qwen3-4B** | **Jan-4B** | **WebSailor-3B** | **II-Search-4B** |
+| --- | --- | --- | --- | --- |
+| # Search | 1.0 | 0.9 | 2.1 | 2.2 |
+| # Visit | 0.1 | 1.9 | 6.4 | 3.5 |
+| # Total Tools | 1.1 | 2.8 | 8.5 | 5.7 |
+
+All benchmark traces from models can be found at: https://huggingface.co/datasets/Intelligent-Internet/II-Search-Benchmark-Details
+
+## Intended Use
+
+II-Search-4B is designed for:
+
+- Information seeking and factual question answering
+- Research assistance and comprehensive report generation
+- Fact verification and evidence-based reasoning
+- Educational and research applications requiring factual accuracy
+
+## Usage
+To deploy and interact with the II-Search-4B model effectively, follow these options:
+1. Serve the model using vLLM or SGLang
+
+Use the following command to serve the model with vLLM (adjust parameters as needed for your hardware setup):
+```bash
+vllm serve Intelligent-Internet/II-Search-4B --served-model-name II-Search-4B --tensor-parallel-size 8 --enable-reasoning --reasoning-parser deepseek_r1 --rope-scaling '{"rope_type":"yarn","factor":1.5,"original_max_position_embeddings":98304}' --max-model-len 131072
+```
+This configuration enables distributed tensor parallelism across 8 GPUs, reasoning capabilities, custom RoPE scaling for extended context, and a maximum context length of 131,072 tokens.
+
+2. Integrate web_search and web_visit tools
+
+Equip the served model with web_search and web_visit tools to enable internet-aware functionality. Alternatively, use a middleware like MCP for tool integration—see this example repository: https://github.com/hoanganhpham1006/mcp-server-template.
+
+## Host on macOS with MLX for local use
+ As an alternative for Apple Silicon users, host the quantized [II-Search-4B-MLX](https://huggingface.co/Intelligent-Internet/II-Search-4B-MLX) version on your Mac. Then, interact with it via user-friendly interfaces like LM Studio or Ollama Desktop.
+
+## Recommended Generation Parameters
+
+```python
+generate_cfg = {
+    'top_k': 20,
+    'top_p': 0.95,
+    'temperature': 0.6,
+    'repetition_penalty': 1.1,
+    'max_tokens': 2048
+}
+```
+
+- For a query that you need to find a short and accurate answer. Add the following phrase: "\n\nPlease reason step-by-step and put the final answer within \\\\boxed{}."
+
+## Citation
+
+```
+@misc{II-Search-4B,
+  author = {Intelligent Internet},
+  title = {II-Search-4B: Information Seeking and Web-Integrated Reasoning LLM},
+  year = {2025},
+  publisher = {Hugging Face},
+  journal = {Hugging Face Hub},
+  howpublished = {\url{https://huggingface.co/II-Vietnam/II-Search-4B}},
+}
+
+```
+
+<!--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! 😊