Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,85 @@
+*.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
+f16/watt-tool-70B-F16-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+f16/watt-tool-70B-F16-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+f16/watt-tool-70B-F16-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+f16/watt-tool-70B-F16-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-f16_q8_0-Q8_0/watt-tool-70B-f16_q8_0-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-f16_q8_0-Q8_0/watt-tool-70B-f16_q8_0-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-bf16_q8_0-Q8_0/watt-tool-70B-bf16_q8_0-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-bf16_q8_0-Q8_0/watt-tool-70B-bf16_q8_0-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+q6_k/watt-tool-70B-f16_q6_k-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+q6_k/watt-tool-70B-f16_q6_k-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+q6_k/watt-tool-70B-bf16_q6_k-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+q6_k/watt-tool-70B-bf16_q6_k-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+q6_k/watt-tool-70B-q6_k_l-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+q6_k/watt-tool-70B-q6_k_l-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+q6_k/watt-tool-70B-q6_k_m-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+q6_k/watt-tool-70B-q6_k_m-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q8_0-Q8_0/watt-tool-70B-q8_0-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q8_0-Q8_0/watt-tool-70B-q8_0-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q5_1_l-Q5_1/watt-tool-70B-q5_1_l-Q5_1-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-q5_1_l-Q5_1/watt-tool-70B-q5_1_l-Q5_1-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+watt-tool-70B-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix/watt-tool-70B.imatrix filter=lfs diff=lfs merge=lfs -text
+iq1-m/watt-tool-70B-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+iq2-xs/watt-tool-70B-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+iq2-xxs/watt-tool-70B-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+iq2-s/watt-tool-70B-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+iq2-m/watt-tool-70B-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+iq3-xs/watt-tool-70B-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+iq3-xxs/watt-tool-70B-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+iq3-s/watt-tool-70B-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+iq3-m/watt-tool-70B-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+iq4-xs/watt-tool-70B-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+iq4-nl/watt-tool-70B-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,368 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- meta-llama/Llama-3.3-70B-Instruct
+tags:
+- function-calling
+- tool-use
+- llama
+- bfcl
+---
+
+# <span style="color: #7FFF7F;">watt-ai/watt-tool-70B 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**  
+
+### `watt-ai/watt-tool-70B-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**.  
+
+### `watt-ai/watt-tool-70B-f16.gguf`  
+- Model weights stored in **F16**.  
+- Use if your device supports **FP16**, especially if BF16 is not available.  
+
+### `watt-ai/watt-tool-70B-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.  
+
+### `watt-ai/watt-tool-70B-f16-q8_0.gguf`  
+- **Output & embeddings** remain in **F16**.  
+- All other layers quantized to **Q8_0**.    
+
+### `watt-ai/watt-tool-70B-q4_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q4_K**.  
+- Good for **CPU inference** with limited memory.  
+
+### `watt-ai/watt-tool-70B-q4_k_s.gguf`  
+- Smallest **Q4_K** variant, using less memory at the cost of accuracy.  
+- Best for **very low-memory setups**.  
+
+### `watt-ai/watt-tool-70B-q6_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q6_K** .  
+
+### `watt-ai/watt-tool-70B-q8_0.gguf`  
+- Fully **Q8** quantized model for better accuracy.  
+- Requires **more memory** but offers higher precision.  
+
+### `watt-ai/watt-tool-70B-iq3_xs.gguf`  
+- **IQ3_XS** quantization, optimized for **extreme memory efficiency**.  
+- Best for **ultra-low-memory devices**.  
+
+### `watt-ai/watt-tool-70B-iq3_m.gguf`  
+- **IQ3_M** quantization, offering a **medium block size** for better accuracy.  
+- Suitable for **low-memory devices**.  
+
+### `watt-ai/watt-tool-70B-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 :)  
+
+
+
+
+# watt-tool-70B
+
+watt-tool-70B is a fine-tuned language model based on LLaMa-3.3-70B-Instruct, optimized for tool usage and multi-turn dialogue. It achieves state-of-the-art performance on the Berkeley Function-Calling Leaderboard (BFCL).
+
+## Model Description
+
+This model is specifically designed to excel at complex tool usage scenarios that require multi-turn interactions, making it ideal for empowering platforms like [Lupan](https://lupan.watt.chat), an AI-powered workflow building tool. By leveraging a carefully curated and optimized dataset, watt-tool-70B demonstrates superior capabilities in understanding user requests, selecting appropriate tools, and effectively utilizing them across multiple turns of conversation.
+
+Target Application: AI Workflow Building as in [https://lupan.watt.chat/](https://lupan.watt.chat/) and [Coze](https://www.coze.com/).
+
+## Key Features
+
+*   **Enhanced Tool Usage:** Fine-tuned for precise and efficient tool selection and execution.
+*   **Multi-Turn Dialogue:** Optimized for maintaining context and effectively utilizing tools across multiple turns of conversation, enabling more complex task completion.
+*   **State-of-the-Art Performance:** Achieves top performance on the BFCL, demonstrating its capabilities in function calling and tool usage.
+*   **Based on LLaMa-3.1-70B-Instruct:** Inherits the strong language understanding and generation capabilities of the base model.
+
+## Training Methodology
+
+watt-tool-70B is trained using supervised fine-tuning on a specialized dataset designed for tool usage and multi-turn dialogue. We use CoT techniques to synthesize high-quality multi-turn dialogue data.
+
+The training process is inspired by the principles outlined in the paper: ["Direct Multi-Turn Preference Optimization for Language Agents"](https://arxiv.org/abs/2406.14868).
+We use SFT and DMPO to further enhance the model's performance in multi-turn agent tasks.
+
+## How to Use
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "watt-ai/watt-tool-70B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype='auto', device_map="auto")
+
+# Example usage (adapt as needed for your specific tool usage scenario)
+"""You are an expert in composing functions. You are given a question and a set of possible functions. Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
+If none of the function can be used, point it out. If the given question lacks the parameters required by the function, also point it out.
+You should only return the function call in tools call sections.
+
+If you decide to invoke any of the function(s), you MUST put it in the format of [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]
+You SHOULD NOT include any other text in the response.
+Here is a list of functions in JSON format that you can invoke.\n{functions}\n
+"""
+# User query
+query = "Find me the sales growth rate for company XYZ for the last 3 years and also the interest coverage ratio for the same duration."
+
+tools = [
+    {
+        "name": "financial_ratios.interest_coverage", "description": "Calculate a company's interest coverage ratio given the company name and duration",
+        "arguments": {
+            "type": "dict",
+            "properties": {
+                "company_name": {
+                    "type": "string",
+                    "description": "The name of the company."
+                }, 
+                "years": {
+                    "type": "integer",
+                    "description": "Number of past years to calculate the ratio."
+                }
+            }, 
+            "required": ["company_name", "years"]
+        }
+    },
+    {
+        "name": "sales_growth.calculate",
+        "description": "Calculate a company's sales growth rate given the company name and duration",
+        "arguments": {
+            "type": "dict", 
+            "properties": {
+                "company": {
+                    "type": "string",
+                    "description": "The company that you want to get the sales growth rate for."
+                }, 
+                "years": {
+                    "type": "integer",
+                    "description": "Number of past years for which to calculate the sales growth rate."
+                }
+            }, 
+            "required": ["company", "years"]
+        }
+    },
+    {
+        "name": "weather_forecast",
+        "description": "Retrieve a weather forecast for a specific location and time frame.",
+        "arguments": {
+            "type": "dict",
+            "properties": {
+                "location": {
+                    "type": "string",
+                    "description": "The city that you want to get the weather for."
+                }, 
+                "days": {
+                    "type": "integer",
+                    "description": "Number of days for the forecast."
+                }
+            },
+            "required": ["location", "days"]
+        }
+    }
+]
+
+messages = [
+    {'role': 'system', 'content': system_prompt.format(functions=tools)},
+    {'role': 'user', 'content': query}
+]
+inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))

f16/watt-tool-70B-F16-00001-of-00004.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:365bcd96fa9cf4c7704523f4627bd3303a913517a8b2de34f616752b84e3766f
+size 45902462976

f16/watt-tool-70B-F16-00002-of-00004.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b298ac077d91cab49dd1709331b1ada89cc8e7031b1e29e96b7291de7cbd87f9
+size 45902462976

f16/watt-tool-70B-F16-00003-of-00004.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52aa7372a3c08dcbbb214cec7d4d9158e6bcebcad85abfe8bd453bb1c7c13533
+size 45902462976

f16/watt-tool-70B-F16-00004-of-00004.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ae95eb4a0dfa4309fc6330554478b86712833b047ffa6fc9e82d80b1a52509
+size 3410528992

imatrix/watt-tool-70B.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d4615e76dea93033daca969d30ddd7a4b107945313160cdf86003c6eb49fd7
+size 24922298

iq1-m/watt-tool-70B-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d510cd6d589b4e39a0467a97dde0053750e760d4db48312c859411191856775
+size 19220696032

iq2-m/watt-tool-70B-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c110bca93b66545817b0b1a31d65c887d56a0dfa12ece262f937a9556d48e1c
+size 27142687712

iq2-s/watt-tool-70B-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22db5ea5bcaa8330f707a64bf31157c5fffbde3b01773ff63a7dc77f4cd626c
+size 25779538912

iq2-xs/watt-tool-70B-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc378e36ffebb15116a90a166f18d536ec235f798f085bb11e524a2fe454dbbb
+size 22455552992

iq2-xxs/watt-tool-70B-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5629768034373ef59cb4272a8eb859bf9c7fd4d5fbfc9571278b1a8df186b3c8
+size 20924632032

iq3-m/watt-tool-70B-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a05bab0e46e5a7c322bc7d5cada563a11f38a1789b9880ea629a40d5052fbc
+size 32068373472

iq3-s/watt-tool-70B-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb92fb8bf698dbaa1f178756508e80df5b0a4de1158a527392ce8437d3409dd
+size 31043390432

iq3-xs/watt-tool-70B-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b8e748d675a6c803c92aa16c8db1537dbf0d890c724b86a2ca7bbfccfc166f
+size 29439069152

iq3-xxs/watt-tool-70B-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2d6cfb8ae99e2d002e718e0e436e9be0588fb45775c116f8427f1a319f4383
+size 27740376032

iq4-nl/watt-tool-70B-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352756bbfa3462c952a1f7c847cafe793b4b7a6b24ff4d8dabbcd9497cdcf3df
+size 40053623776

iq4-xs/watt-tool-70B-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7420d87377994e5c8e4b04cc2ac613ad4017a192ebba8f08d495963d0fdee503
+size 37902666720

q6_k/watt-tool-70B-bf16_q6_k-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31ac9b397119a08e3c9a201fd5d8f313928fc0d46f5ae5b75d69c68dd4421db
+size 45902462976

q6_k/watt-tool-70B-bf16_q6_k-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d73bff96e97c9024392859a87be0264e81d5dccba5cca77cbd62745a24a5e8
+size 14464617472

q6_k/watt-tool-70B-q6_k_l-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec5738c39c6e2c38378c524f754bcf206c8a4cbebdc2f34d46ffd0db2c59e3d
+size 45902462976

q6_k/watt-tool-70B-q6_k_l-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303d8f7e4a3c1e5bd4f5731c81d4cb3f5deb9de5918da10212939551b9a39986
+size 12494605312

q6_k/watt-tool-70B-q6_k_m-Q6_K-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d717649a15a7e11351d9fdb026a4b8ae5476977e1ee45b4bc21e71457beb5fa1
+size 45902462976

q6_k/watt-tool-70B-q6_k_m-Q6_K-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504be18e2195f8712da96c6b937bfaeefbf83f76612ba3546b496c8ea04944b9
+size 11985685504

watt-tool-70B-bf16_q8_0-Q8_0/watt-tool-70B-bf16_q8_0-Q8_0-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac13b74062a79da93cf8766a2a601073c6081d0ec466c1146de2ee6264f63e1
+size 45902462976

watt-tool-70B-bf16_q8_0-Q8_0/watt-tool-70B-bf16_q8_0-Q8_0-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc057b13e37f4b534d1148fc0840c9398b1c841c1b38062c30083dbcd2c3ca6e
+size 31042603744

watt-tool-70B-f16_q8_0-Q8_0/watt-tool-70B-f16_q8_0-Q8_0-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58b8b29ddc23f3ca26aef7680fd64a7fcc942c04d49f0b3e16ac60cded54f9f
+size 45902462976

watt-tool-70B-f16_q8_0-Q8_0/watt-tool-70B-f16_q8_0-Q8_0-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc057b13e37f4b534d1148fc0840c9398b1c841c1b38062c30083dbcd2c3ca6e
+size 31042603744

watt-tool-70B-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdaeea982d2476351caecd48a79bfd1a7d3542089eac0ce3f001583f1f2284f7
+size 18198334464

watt-tool-70B-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53ef013101f67f7be6149ef3c84f32c9d101e1a1da1a6fd8b2897f5799f5ff2
+size 24709991424

watt-tool-70B-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fab75261c6b56189e7bc97267d4766f39b0a7de0b383caf58142b6b8a4bb977
+size 34677918720

watt-tool-70B-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99da2ca05d13bab56032594e0ede4e5c00adb3879a6198c7605144aa6038c3f3
+size 31043390464

watt-tool-70B-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bac20a2e28d8906072f4a8d4e4fb2b10e924ec0e809d10289f36d67bfe7979d
+size 39698861056

watt-tool-70B-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13f88e37f48c62df11db809bf4266f3b84a27c71bdd96254b7d6fb23d47f402
+size 44108385280

watt-tool-70B-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d8854c88e0771e21e834c3f83ba6e0bb5cec32a291f46db6daf3fa01ddbdae
+size 42791275520

watt-tool-70B-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad6f03ea2672f818d44d3208c56eed32e934efb9eec55c5d918ba300b3a6ff5
+size 40618101760

watt-tool-70B-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e130cc732e1abb2768d92ee84688d3b7ea197482f2d9f0fdbb1bf1dc47a23bee
+size 48517909504

watt-tool-70B-q5_1_l-Q5_1/watt-tool-70B-q5_1_l-Q5_1-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdec1cc1c0ca3abe0451f3b4c5fd1723c6d5ff9a62987e78bc943fed50ef03ae
+size 45902462976

watt-tool-70B-q5_1_l-Q5_1/watt-tool-70B-q5_1_l-Q5_1-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af13a493157b5f1f343f30d3e58c2a4c1f6d3a15ddc7f54fc67d28e7776e6eb
+size 7681641472

watt-tool-70B-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d291afa9de2bbb4e75779e1a11a50d1f26cb9252e9fffa146560ecce6ca31c
+size 48796994560

watt-tool-70B-q8_0-Q8_0/watt-tool-70B-q8_0-Q8_0-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655b9f410171f5c03190a59b7621bdb2be11d0a59ce113f4fc1e33479a6990b1
+size 45902462976

watt-tool-70B-q8_0-Q8_0/watt-tool-70B-q8_0-Q8_0-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adfb759b2b2c39336a4e04eb1e082674f5b77e64f85f00b262d7939fdad6e5e
+size 29072591584