初始化项目，由ModelHub XC社区提供模型

Model: Mungert/granite-3.3-8b-instruct-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,75 @@
+*.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
+granite-3.3-8b-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct.imatrix filter=lfs diff=lfs merge=lfs -text
+granite-3.3-8b-instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,674 @@
+---
+pipeline_tag: text-generation
+inference: false
+license: apache-2.0
+library_name: transformers
+tags:
+- language
+- granite-3.3
+base_model:
+- ibm-granite/granite-3.3-8b-base
+---
+
+# <span style="color: #7FFF7F;">granite-3.3-8b-instruct GGUF Models</span>
+
+## <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**  
+
+### `granite-3.3-8b-instruct-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**.  
+
+### `granite-3.3-8b-instruct-f16.gguf`  
+- Model weights stored in **F16**.  
+- Use if your device supports **FP16**, especially if BF16 is not available.  
+
+### `granite-3.3-8b-instruct-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.  
+
+### `granite-3.3-8b-instruct-f16-q8_0.gguf`  
+- **Output & embeddings** remain in **F16**.  
+- All other layers quantized to **Q8_0**.    
+
+### `granite-3.3-8b-instruct-q4_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q4_K**.  
+- Good for **CPU inference** with limited memory.  
+
+### `granite-3.3-8b-instruct-q4_k_s.gguf`  
+- Smallest **Q4_K** variant, using less memory at the cost of accuracy.  
+- Best for **very low-memory setups**.  
+
+### `granite-3.3-8b-instruct-q6_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q6_K** .  
+
+### `granite-3.3-8b-instruct-q8_0.gguf`  
+- Fully **Q8** quantized model for better accuracy.  
+- Requires **more memory** but offers higher precision.  
+
+### `granite-3.3-8b-instruct-iq3_xs.gguf`  
+- **IQ3_XS** quantization, optimized for **extreme memory efficiency**.  
+- Best for **ultra-low-memory devices**.  
+
+### `granite-3.3-8b-instruct-iq3_m.gguf`  
+- **IQ3_M** quantization, offering a **medium block size** for better accuracy.  
+- Suitable for **low-memory devices**.  
+
+### `granite-3.3-8b-instruct-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/dashboard)  
+
+💬 **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 :)  
+
+
+
+# Granite-3.3-8B-Instruct
+
+**Model Summary:**
+Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities. Built on top of Granite-3.3-8B-Base, the model delivers significant gains on benchmarks for measuring generic performance including AlpacaEval-2.0 and Arena-Hard, and improvements in mathematics, coding, and instruction following. It supprts structured reasoning through \<think\>\<\/think\> and \<response\>\<\/response\> tags, providing clear separation between internal thoughts and final outputs. The model has been trained on a carefully balanced combination of permissively licensed data and curated synthetic tasks.
+
+- **Developers:** Granite Team, IBM
+- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
+- **Release Date**: April 16th, 2025
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+
+**Supported Languages:** 
+English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. However, users may finetune this Granite model for languages beyond these 12 languages.
+
+**Intended Use:** 
+This model is designed to handle general instruction-following tasks and can be integrated into AI assistants across various domains, including business applications.
+
+**Capabilities**
+* Thinking
+* Summarization
+* Text classification
+* Text extraction
+* Question-answering
+* Retrieval Augmented Generation (RAG)
+* Code related tasks
+* Function-calling tasks
+* Multilingual dialog use cases
+* Fill-in-the-middle
+* Long-context tasks including long document/meeting summarization, long document QA, etc.
+
+
+**Generation:** 
+This is a simple example of how to use Granite-3.3-8B-Instruct model.
+
+Install the following libraries:
+
+```shell
+pip install torch torchvision torchaudio
+pip install accelerate
+pip install transformers
+```
+Then, copy the snippet from the section that is relevant for your use case.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, set_seed
+import torch
+
+model_path="ibm-granite/granite-3.3-8b-instruct"
+device="cuda"
+model = AutoModelForCausalLM.from_pretrained(
+        model_path,
+        device_map=device,
+        torch_dtype=torch.bfloat16,
+    )
+tokenizer = AutoTokenizer.from_pretrained(
+        model_path
+)
+
+conv = [{"role": "user", "content":"Redesign a common household item to make it more sustainable and user-friendly. Explain the changes and their benefits."}]
+
+input_ids = tokenizer.apply_chat_template(conv, return_tensors="pt", thinking=True, return_dict=True, add_generation_prompt=True).to(device)
+
+set_seed(42)
+output = model.generate(
+    **input_ids,
+    max_new_tokens=8192,
+)
+
+prediction = tokenizer.decode(output[0, input_ids["input_ids"].shape[1]:], skip_special_tokens=True)
+print(prediction)
+```
+
+**Example Outputs**
+- thinking=True
+```md
+<think>To address this prompt, I'll focus on redesigning a common household item: the plastic water bottle. The goal is to make it more sustainable and user-friendly. Here are the proposed changes and their benefits:
+
+1. **Material**: Replace plastic with biodegradable or recyclable materials like glass or plant-based plastics (PLA).
+2. **Design**: Introduce a modular design for easy refilling and cleaning.
+3. **Functionality**: Incorporate a built-in water filter for purification.
+4. **Durability**: Enhance the bottle's lifespan through robust construction.
+5. **User-friendliness**: Simplify the cap mechanism for easy opening and closing.
+
+These changes would significantly reduce plastic waste, promote recycling, ensure access to clean drinking water, and enhance the overall user experience.
+
+Now, I will detail each change and its benefits in a structured format.</think>
+
+<response>### Redesign of the Plastic Water Bottle for Sustainability and User-Friendliness
+
+#### 1. Material: Biodegradable or Recyclable Alternatives
+
+**Change**: Transition from traditional PET plastic to glass or plant-based plastics (Polylactic Acid - PLA).
+
+**Benefits**:
+- **Sustainability**: Glass and PLA are biodegradable or highly recyclable, drastically reducing plastic pollution.
+- **Health**: Unlike PET, these materials do not leach chemicals into the water, ensuring safer consumption.
+
+#### 2. Modular Design for Easy Refilling and Cleaning
+
+**Change**: Implement a detachable, interchangeable inner liner within a reusable outer casing.
+
+**Benefits**:
+- **User-Friendliness**: Users can easily remove the inner liner for thorough cleaning, reducing the risk of bacterial growth.
+- **Sustainability**: The outer casing remains intact, encouraging reuse, while the inner liner can be replaced or recycled when worn out.
+
+#### 3. Built-in Water Filter
+
+**Change**: Integrate a removable, replaceable water filter into the bottle cap.
+
+**Benefits**:
+- **Accessibility**: Provides clean drinking water directly from any source (tap, river, etc.), eliminating the need for additional filtration devices.
+- **Health**: Removes contaminants, bacteria, and impurities, ensuring safe hydration.
+- **Sustainability**: Reduces the use of single-use plastic water bottles by offering a purification solution within a reusable container.
+
+#### 4. Enhanced Durability
+
+**Change**: Use high-quality, durable materials and robust construction techniques for both the outer casing and inner liner.
+
+**Benefits**:
+- **Longevity**: A more robust design increases the bottle's lifespan, reducing the frequency of replacements.
+- **Cost-effectiveness**: Although the initial cost might be higher, the long-term savings from reduced replacements make it economical.
+- **Sustainability**: Less frequent disposal means lower environmental impact.
+
+#### 5. Simplified Cap Mechanism
+
+**Change**: Adopt a one-touch, easy-to-open and close cap design, possibly inspired by sports bottle caps.
+
+**Benefits**:
+- **User-Friendliness**: Especially beneficial for children, elderly, or those with limited hand dexterity.
+- **Convenience**: Quick access to water encourages more frequent hydration, promoting healthier habits.
+
+### Conclusion
+
+This redesigned water bottle addresses key sustainability concerns by minimizing plastic use and waste, while also enhancing user-friendliness through improved functionality, durability, and accessibility. By integrating biodegradable materials, a modular design, a built-in filter, robust construction, and a simple cap mechanism, the bottle not only reduces environmental footprint but also offers a superior user experience.</response>
+```
+- thinking=False
+```md
+Item for Redesign: Plastic Bottle (e.g., water or beverage bottle)
+
+Redesign Concept: Eco-Friendly, Modular, and Multi-Functional Reusable Bottle
+
+Changes:
+
+1. Material: Replace the conventional plastic with food-grade, BPA-free, and recyclable materials such as stainless steel or glass. These materials are durable, non-toxic, and have a longer lifespan, reducing waste.
+
+2. Modular Design: Introduce a modular design that allows users to customize their bottle according to their needs. This could include interchangeable caps, mouthpiece sizes, and carrying loops. Users can purchase additional modules as needed, promoting a more sustainable approach by reducing the need to buy an entirely new bottle for different purposes.
+
+3. Integrated Filter: Incorporate a built-in, washable, and reusable filter that can remove impurities and improve the taste of water. This eliminates the need for single-use disposable filters or bottled water, further reducing plastic waste.
+
+4. Smart Cap: Develop a smart cap with a built-in digital display and temperature sensor. This feature allows users to track their daily water intake, set hydration goals, and monitor the temperature of their beverage. The smart cap can be synced with a mobile app for additional functionality, such as reminders and progress tracking.
+
+5. Easy-to-Clean Design: Ensure the bottle has a wide mouth and smooth interior surfaces for easy cleaning. Include a brush for hard-to-reach areas, making maintenance simple and encouraging regular use.
+
+6. Collapsible Structure: Implement a collapsible design that reduces the bottle's volume when not in use, making it more portable and convenient for storage.
+
+Benefits:
+
+1. Sustainability: By using recyclable materials and reducing plastic waste, this redesigned bottle significantly contributes to a more sustainable lifestyle. The modular design and reusable filter also minimize single-use plastic consumption.
+
+2. User-Friendly: The smart cap, easy-to-clean design, and collapsible structure make the bottle convenient and user-friendly. Users can customize their bottle to suit their needs, ensuring a better overall experience.
+
+3. Healthier Option: Using food-grade, BPA-free materials and an integrated filter ensures that the beverages consumed are free from harmful chemicals and impurities, promoting a healthier lifestyle.
+
+4. Cost-Effective: Although the initial investment might be higher, the long-term savings from reduced purchases of single-use plastic bottles and disposable filters make this reusable bottle a cost-effective choice.
+
+5. Encourages Hydration: The smart cap's features, such as hydration tracking and temperature monitoring, can motivate users to stay hydrated and develop healthier habits.
+
+By redesigning a common household item like the plastic bottle, we can create a more sustainable, user-friendly, and health-conscious alternative that benefits both individuals and the environment.
+```
+
+**Evaluation Results:**
+<table>
+<thead>
+    <caption style="text-align:center"><b>Comparison with different models over various benchmarks<sup id="fnref1"><a href="#fn1">1</a></sup>. Scores of AlpacaEval-2.0 and Arena-Hard are calculated with thinking=True</b></caption>
+  <tr>
+    <th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">Arena-Hard</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">AlpacaEval-2.0</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">MMLU</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">PopQA</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">TruthfulQA</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">BigBenchHard<sup id="fnref2"><a href="#fn2">2</a></sup></th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">DROP<sup id="fnref3"><a href="#fn3">3</a></sup></th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">GSM8K</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">HumanEval</th>
+   <th style="text-align:center; background-color: #001d6c; color: white;">HumanEval+</th>
+  <th style="text-align:center; background-color: #001d6c; color: white;">IFEval</th>
+  <th style="text-align:center; background-color: #001d6c; color: white;">AttaQ</th>
+  </tr></thead>
+  <tbody>
+<tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.1-2B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">23.3</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">27.17</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">57.11</td> 
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">20.55</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">59.79</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">61.82</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">20.99</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">67.55</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">79.45</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">75.26</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">63.59</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">84.7</td>
+  </tr>
+  <tr>
+      <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.2-2B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">24.86</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">34.51</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">57.18</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">20.56</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">59.8</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">61.39</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">23.84</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">67.02</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">80.13</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">73.39</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">61.55</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">83.23</td>
+  </tr>
+  <tr>
+      <td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-2B-Instruct</b></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 28.86 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 43.45 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 55.88 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 18.4 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 58.97 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 63.91 </td>
+      <td style="text-align:center; background-color: #DAE8FF; color: black;"> 44.33 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 72.48 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 80.51 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 75.68 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 65.8 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">87.47</td>
+      </tr>
+      
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Llama-3.1-8B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">36.43</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">27.22</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">69.15</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">28.79</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">52.79</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">73.43</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">71.23</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">83.24</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">85.32</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">80.15</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">79.10</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">83.43</td>
+  </tr>
+           
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">DeepSeek-R1-Distill-Llama-8B</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">17.17</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">21.85</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">45.80</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">13.25</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">47.43</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">67.39</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">49.73</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">72.18</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">67.54</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">62.91</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">66.50</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">42.87</td>
+  </tr>
+      
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Qwen-2.5-7B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">25.44</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">30.34</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">74.30</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">18.12</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">63.06</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">69.19</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">64.06</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">84.46</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">93.35</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">89.91</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">74.90</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">81.90</td>
+  </tr>
+      
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">DeepSeek-R1-Distill-Qwen-7B</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">10.36</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">15.35</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">50.72</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">9.94</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">47.14</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">67.38</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">51.78</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">78.47</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">79.89</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">78.43</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">59.10</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">42.45</td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.1-8B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">37.58</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">30.34</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">66.77</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">28.7</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">65.84</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">69.87</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">58.57</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">79.15</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">89.63</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">85.79</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">73.20</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">85.73</td>
+  </tr>
+            
+<tr>
+      <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.2-8B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">55.25</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">61.19</td>
+   <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">66.79</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">28.04</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">66.92</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">71.86</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">58.29</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">81.65</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">89.35</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">85.72</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">74.31</td>
+     <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;">84.7</td>
+  </tr>
+  <tr>
+      <td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-8B-Instruct</b></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 57.56 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 62.68 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 65.54 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 26.17 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 66.86 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 69.13 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 59.36 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 80.89 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 89.73 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 86.09 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 74.82 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;">88.5</td>
+      </tr>                 
+</tbody></table>
+
+<table>
+ <caption style="text-align:center"><b>Math Benchmarks</b></caption>
+<thead>
+  <tr>
+    <th style="text-align:left; background-color: #001d6c; color: white;">Models</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">AIME24</th>
+    <th style="text-align:center; background-color: #001d6c; color: white;">MATH-500</th>
+  </tr></thead>
+  <tbody>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.1-2B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 0.89 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 35.07 </td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.2-2B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 0.89 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 35.54 </td>
+  </tr>
+  <tr>
+      <td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-2B-Instruct</b></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 3.28 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 58.09 </td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.1-8B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 1.97 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 48.73 </td>
+  </tr>
+  <tr>
+    <td style="text-align:left; background-color: #FFFFFF; color: #2D2D2D;">Granite-3.2-8B-Instruct</td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 2.43 </td>
+    <td style="text-align:center; background-color: #FFFFFF; color: #2D2D2D;"> 52.8 </td>
+  </tr>
+  <tr>
+      <td style="text-align:left; background-color: #DAE8FF; color: black;"><b>Granite-3.3-8B-Instruct</b></td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 8.12 </td>
+    <td style="text-align:center; background-color: #DAE8FF; color: black;"> 69.02 </td>
+  </tr>
+    </tbody></table>
+    
+**Training Data:** 
+Overall, our training data is largely comprised of two key sources: (1) publicly available datasets with permissive license, (2) internal synthetically generated data targeted to enhance reasoning capabilites. 
+<!-- A detailed attribution of datasets can be found in [Granite 3.2 Technical Report (coming soon)](#), and [Accompanying Author List](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/author-ack.pdf). -->
+
+**Infrastructure:**
+We train Granite-3.3-8B-Instruct using IBM's super computing cluster, Blue Vela, which is outfitted with NVIDIA H100 GPUs. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs.
+
+**Ethical Considerations and Limitations:** 
+Granite-3.3-8B-Instruct builds upon Granite-3.3-8B-Base, leveraging both permissively licensed open-source and select proprietary data for enhanced performance. Since it inherits its foundation from the previous model, all ethical considerations and limitations applicable to [Granite-3.3-8B-Base](https://huggingface.co/ibm-granite/granite-3.3-8b-base) remain relevant.
+
+
+**Resources**
+- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite
+- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/
+- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources
+
+<p><a href="#fnref1" title="Jump back to reference">[1]</a> Evaluated using <a href="https://github.com/allenai/olmes">OLMES</a> (except AttaQ and Arena-Hard scores)</p>
+<p><a href="#fnref2" title="Jump back to reference">[2]</a> Added regex for more efficient asnwer extraction.</a></p>
+<p><a href="#fnref3" title="Jump back to reference">[3]</a> Modified the implementation to handle some of the issues mentioned <a href="https://huggingface.co/blog/open-llm-leaderboard-drop">here</a></p>
+<!-- ## Citation
+<!-- ## Citation
+```
+@misc{granite-models,
+  author = {author 1, author2, ...},
+  title = {},
+  journal = {},
+  volume = {},
+  year = {2024},
+  url = {https://arxiv.org/abs/0000.00000},
+}
+``` -->

granite-3.3-8b-instruct-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33271135a06438842c1a77b55a7f3be21e439169ad277570a46217abd7e0b3d4
+size 16344139712

granite-3.3-8b-instruct-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10e9f8e62ed7c8efae3768a6ced6b090c8a645d218bc88d137ae6b27c5efc3d
+size 8873035712

granite-3.3-8b-instruct-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a867f2dc0428c622e1a41691c514b865745e57cc9bd93adccf2cc3ca0acad88b
+size 8873035712

granite-3.3-8b-instruct-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:653590b5c457c4def6656878ff1bbf820905ca2d1bac723e1c8ddf11a517c7d0
+size 2836837856

granite-3.3-8b-instruct-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4294c7d03d2088627538211e3cca03b4085d3f6b3132cfa334210e45aeb77772
+size 2265609696

granite-3.3-8b-instruct-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55578409bf54ceecacdae8c341b6a1a0efd3a9a6235884627b755469d74bbad3
+size 3711989216

granite-3.3-8b-instruct-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f25ca63dfb46231e2950e766e92e2bb5bbb1fc33de3feb592655ee3eeb45c3a
+size 3588044256

granite-3.3-8b-instruct-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084910f651ca78e153bf1ec0a35c9f464e715bf0b6c6c2f4b5c38433856c8ba8
+size 3401266656

granite-3.3-8b-instruct-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b71dc986f1704b337c288c4584ab4c6e472b5f033693a47419e3095d996e716
+size 3201381856

granite-3.3-8b-instruct-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e01e208d2c26d4f49c666c420397c4f167001b41957ec39f4991bf8273f9787c
+size 4671882432

granite-3.3-8b-instruct-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2964a6dcec8c16977a4d3ce7db2d86cb78460b31d624b3add20cec996a724d21
+size 4428088512

granite-3.3-8b-instruct-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9538a66e81670e83139bb57f3d35a51cbcfa32421743ebdf1943e7fc6fda0d68
+size 3103605952

granite-3.3-8b-instruct-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ec372881744b45442e2c1c23e0c1bf299ddb3923cef9d6450863b4b891b6f9
+size 2857154016

granite-3.3-8b-instruct-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab425c3d10c69ef32d91ad36b45cb99ffc9d53cc838f527214c7d4d5c65571b5
+size 3996599488

granite-3.3-8b-instruct-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7c9a22119a03b53f4c9f0506b72e734bce9b09a8f269b3e54a4978e3202d70
+size 3565762016

granite-3.3-8b-instruct-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37348326e5105ed93ab961a199d3efa31533b3c63fb2a725555e1670aefe0545
+size 4598999008

granite-3.3-8b-instruct-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d36612719566453c6ae20cae3479fa9b482f337aeb8f17ed0f4d378976866c
+size 5109657312

granite-3.3-8b-instruct-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cade9d14c817993c2b87505508b2dce4781d61470a43e415f69af8f86b805670
+size 4942873792

granite-3.3-8b-instruct-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b8f9e0f25991fe89bec33b39ce7787c5f1a9dfa804c4ea5a7153a8ca1a741d
+size 4685776064

granite-3.3-8b-instruct-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27d9544493505e26b0dec797825e4b01b7f9659f577fe1c104399cf6d9fb0a85
+size 5620315616

granite-3.3-8b-instruct-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0737ad3870eb820289b6bd74ca3e8018e15ce1686ccc66d3010333e1b34339f6
+size 6130973920

granite-3.3-8b-instruct-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb664d9ec4533e03c5026279dbdc3dacf36f340a205e0d170e5014bd8a6f552
+size 5797463232

granite-3.3-8b-instruct-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26555401c1a3620a4dc48045cb2746ef1f82ec04fce81dcb404075ce878453d
+size 5647058112

granite-3.3-8b-instruct-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa23bd246388de9b4eb6af19d27ba32a1c12feb9daf0f4b22eb206ada8ebf21
+size 6705464512

granite-3.3-8b-instruct-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4238ad0f24527645ae37f1d6423b5dccc01e39f18927f91851abe03eac255a
+size 8684265152

granite-3.3-8b-instruct.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b456077329eb485547768df1b3aaeab4164fe9e33419325e2e8ec0df0a1555bb
+size 5989458