Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,80 @@
+*.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
+functionary-small-v3.1-f16.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-f16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-bf16-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-f16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-bf16-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-f16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-bf16-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1.imatrix filter=lfs diff=lfs merge=lfs -text
+functionary-small-v3.1-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,315 @@
+---
+license: mit
+---
+
+# <span style="color: #7FFF7F;">functionary-small-v3.1 GGUF Models</span>
+
+## **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**  
+
+### `functionary-small-v3.1-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**.  
+
+### `functionary-small-v3.1-f16.gguf`  
+- Model weights stored in **F16**.  
+- Use if your device supports **FP16**, especially if BF16 is not available.  
+
+### `functionary-small-v3.1-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.  
+
+### `functionary-small-v3.1-f16-q8_0.gguf`  
+- **Output & embeddings** remain in **F16**.  
+- All other layers quantized to **Q8_0**.    
+
+### `functionary-small-v3.1-q4_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q4_K**.  
+- Good for **CPU inference** with limited memory.  
+
+### `functionary-small-v3.1-q4_k_s.gguf`  
+- Smallest **Q4_K** variant, using less memory at the cost of accuracy.  
+- Best for **very low-memory setups**.  
+
+### `functionary-small-v3.1-q6_k.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q6_K** .  
+
+### `functionary-small-v3.1-q8_0.gguf`  
+- Fully **Q8** quantized model for better accuracy.  
+- Requires **more memory** but offers higher precision.  
+
+### `functionary-small-v3.1-iq3_xs.gguf`  
+- **IQ3_XS** quantization, optimized for **extreme memory efficiency**.  
+- Best for **ultra-low-memory devices**.  
+
+### `functionary-small-v3.1-iq3_m.gguf`  
+- **IQ3_M** quantization, offering a **medium block size** for better accuracy.  
+- Suitable for **low-memory devices**.  
+
+### `functionary-small-v3.1-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 ❤ . Also I’d really appreciate it if you could test my Network Monitor Assistant at 👉 [Network Monitor Assitant](https://readyforquantum.com).
+
+💬 Click the **chat icon** (bottom right of the main and dashboard pages) . Choose a LLM; toggle between the LLM Types TurboLLM -> FreeLLM -> TestLLM.
+
+### What I'm Testing
+
+I'm experimenting with **function calling** against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function".
+
+🟡 **TestLLM** – Runs the current testing model using llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! .
+
+### The other Available AI Assistants
+
+🟢 **TurboLLM** – Uses **gpt-4o-mini** Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM .
+
+🔵 **HugLLM** – Runs **open-source Hugging Face models** Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability)
+
+### 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! 😊
+
+
+# Model Card for functionary-small-v3.1
+
+**This model was based on [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)**, using Meta's original prompt template as described in: [User-defined Custom tool calling](https://llama.meta.com/docs/model-cards-and-prompt-formats/llama3_1/#user-defined-custom-tool-calling)
+
+[https://github.com/MeetKai/functionary](https://github.com/MeetKai/functionary)
+
+<img src="https://huggingface.co/meetkai/functionary-medium-v2.2/resolve/main/functionary_logo.jpg" alt="Functionary Logo" width="300"/>
+
+Functionary is a language model that can interpret and execute functions/plugins.
+
+The model determines when to execute functions, whether in parallel or serially, and can understand their outputs. It only triggers functions as needed. Function definitions are given as JSON Schema Objects, similar to OpenAI GPT function calls.
+
+## Key Features
+
+- Intelligent **parallel tool use**
+- Able to analyze functions/tools outputs and provide relevant responses **grounded in the outputs**
+- Able to decide **when to not use tools/call functions** and provide normal chat response
+- Truly one of the best open-source alternative to GPT-4
+- Support code interpreter
+
+## How to Get Started
+
+We provide custom code for parsing raw model responses into a JSON object containing role, content and tool_calls fields. This enables the users to read the function-calling output of the model easily.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("meetkai/functionary-small-v3.1")
+model = AutoModelForCausalLM.from_pretrained("meetkai/functionary-small-v3.1", device_map="auto", trust_remote_code=True)
+
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_current_weather",
+            "description": "Get the current weather",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "The city and state, e.g. San Francisco, CA"
+                    }
+                },
+                "required": ["location"]
+            }
+        }
+    }
+]
+messages = [{"role": "user", "content": "What is the weather in Istanbul and Singapore respectively?"}]
+
+final_prompt = tokenizer.apply_chat_template(messages, tools, add_generation_prompt=True, tokenize=False)
+inputs = tokenizer(final_prompt, return_tensors="pt").to("cuda")
+pred = model.generate_tool_use(**inputs, max_new_tokens=128, tokenizer=tokenizer)
+print(tokenizer.decode(pred.cpu()[0]))
+```
+
+## Prompt Template
+
+We convert function definitions to a similar text to TypeScript definitions. Then we inject these definitions as system prompts. After that, we inject the default system prompt. Then we start the conversation messages.
+
+This formatting is also available via our vLLM server which we process the functions into Typescript definitions encapsulated in a system message using a pre-defined Transformers Jinja chat template. This means that the lists of messages can be formatted for you with the apply_chat_template() method within our server:
+
+```python
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8000/v1", api_key="functionary")
+
+client.chat.completions.create(
+    model="path/to/functionary/model/",
+    messages=[{"role": "user",
+            "content": "What is the weather for Istanbul?"}
+    ],
+    tools=[{
+            "type": "function",
+            "function": {
+                "name": "get_current_weather",
+                "description": "Get the current weather",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "The city and state, e.g. San Francisco, CA"
+                        }
+                    },
+                    "required": ["location"]
+                }
+            }
+        }],
+    tool_choice="auto"
+)
+```
+
+will yield:
+
+```
+<|start_header_id|>system<|end_header_id|>
+
+Environment: ipython
+
+Cutting Knowledge Date: December 2023
+
+
+You have access to the following functions:
+
+Use the function 'get_current_weather' to 'Get the current weather'
+{"name": "get_current_weather", "description": "Get the current weather", "parameters": {"type": "object", "properties": {"location": {"type": "string", "description": "The city and state, e.g. San Francisco, CA"}},"required": ["location"]}}
+
+
+Think very carefully before calling functions.
+If a you choose to call a function ONLY reply in the following format:
+<{start_tag}={function_name}>{parameters}{end_tag}
+where
+
+start_tag => `<function`
+parameters => a JSON dict with the function argument name as key and function argument value as value.
+end_tag => `</function>`
+
+Here is an example,
+<function=example_function_name>{"example_name": "example_value"}</function>
+
+Reminder:
+- If looking for real time information use relevant functions before falling back to brave_search
+- Function calls MUST follow the specified format, start with <function= and end with </function>
+- Required parameters MUST be specified
+- Only call one function at a time
+- Put the entire function call reply on one line
+
+<|eot_id|><|start_header_id|>user<|end_header_id|>
+
+What is the weather for Istanbul?
+```
+
+A more detailed example is provided [here](https://github.com/MeetKai/functionary/blob/main/tests/prompt_test_v3-llama3.1.txt).
+
+## Run the model
+
+We encourage users to run our models using our OpenAI-compatible vLLM server [here](https://github.com/MeetKai/functionary).
+
+# The MeetKai Team
+![MeetKai Logo](https://huggingface.co/meetkai/functionary-medium-v2.2/resolve/main/meetkai_logo.png "MeetKai Logo")

functionary-small-v3.1-bf16-q4_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be57b067950ecbdb9c6a13f38267c1664b2f2597dced8613353914ffbe76cdf4
+size 6295641952

functionary-small-v3.1-bf16-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2dbe8cc0778be4afd9df630156081143b1190b910d81e8c72cb224131628f7
+size 7835475808

functionary-small-v3.1-bf16-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9b571ef9a7c9fe74a2b394d0dce494b362c21cda390772cef6d33e6d6c985e
+size 9525780032

functionary-small-v3.1-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a5dbbe41031a0d9f4adf12044aee7bb5c9a68d3d04f357be085f35053ed291
+size 16068894272

functionary-small-v3.1-f16-q4_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ddc4597b3f7f56f98cc1781eb74acb4b3d2cb7247254d094c4d7eb7e2f67d4
+size 6295641952

functionary-small-v3.1-f16-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802cb8736359b2215c3a0ba074b33f3fb59e8ee2d93660e708c68a3ba3946a87
+size 7835475808

functionary-small-v3.1-f16-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4ae1a899dd12479d7633be01847b14cc4aa306d25833202520ecfdd6379931
+size 9525780032

functionary-small-v3.1-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79df1b9629e70d06ad3cc50e81ce39ff3eb7aea80918d38bd47ab4272060b4c2
+size 2161975136

functionary-small-v3.1-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62bf8af518d2f474e9c534329dd1fdec0436f73a1f732223da421608b56d3c80
+size 2019630944

functionary-small-v3.1-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ea72e098182d31e2a80957e7d33adaf0757f86b5385c31eb4d8da55910be3d
+size 2948284256

functionary-small-v3.1-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b03bded19c7d04a235528595ac02abb8bba1fe9c789047583d13aeb2962ac37
+size 2758492000

functionary-small-v3.1-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a82d573d85ecd22af14863ab1cee0a869e8b48df652ba5d9720f0304ee03d59
+size 2605784928

functionary-small-v3.1-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645015b7097ed3e1184d54ffbc9d9015462dd9fbc6f0853bd8a5031d76ed6c9f
+size 2399215456

functionary-small-v3.1-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd62e021db08bb760bdc70383bac53fa37796c196531942ef0f1af64fbcf5fee
+size 3784826720

functionary-small-v3.1-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73882a8c2829d7958a8b107ded58cbd89e042642a5c32b52aafcac6026369fb
+size 3682328416

functionary-small-v3.1-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa349d3d671786e23b1337f6150aea76d8fac0b941449ec682b990d6ccb867e
+size 3518750560

functionary-small-v3.1-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89aa003930df8e66ce9a87e1e4d342af249bca5bb48fb7f20c3a589e968b0538
+size 3274915680

functionary-small-v3.1-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39718a4cacddedbd60737d6b116066d1881567fc81706878670ff201552787e
+size 4677992288

functionary-small-v3.1-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fab60a5bd5642b387f379b892c36e68bd6e1e32090e0dd97a51ceb5f0cee504
+size 4447666016

functionary-small-v3.1-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e82be5800e7ed1ba84034a439ef6df35d131a1c9fa9bc61146a34ea31909a3e
+size 2988818272

functionary-small-v3.1-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b0c0fc1aafd853f57a9e4735ffd1240a67e29840e5f6dbaddefa5d5df80b03
+size 4018921312

functionary-small-v3.1-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75744fdf6144c4095586b234ebd095c264d5f3efbe3280d1a68f99b15af72d8b
+size 3664502624

functionary-small-v3.1-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac5c9d6c67d23c1eeca5b4c81dfb2c8ed039dab73daeb0a4c2a350ab71259912
+size 4525776736

functionary-small-v3.1-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da9f9d5756a4b06365b9540d26a09ce7938f1d64dc406dcaf34f3ea57773927
+size 5027651424

functionary-small-v3.1-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade1c197f0dfdf6e0199bc25c44259b9e96d7e19ca133b685b898003284bd6ed
+size 4920737632

functionary-small-v3.1-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:969cc3b6a63fc1ffa14e119c0abdd3a92290a0a75a14a861840a19c5977714d9
+size 4692672352

functionary-small-v3.1-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d72c5af879d401af00a1361ba2cab03441cafbffd8618d6d1281d14c360b0f0
+size 5529526112

functionary-small-v3.1-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b92e6061a2682f6eb29984cbd305bf56ce71372de8763c395329e2893e3968
+size 6031400800

functionary-small-v3.1-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4505c5c32d3e971888122e679244b99668ad5a4881a5a042d580e3bfaf0ff8b3
+size 5732990816

functionary-small-v3.1-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b541f9731f633fb33548ac8a86dd5cecfd37eb402ef60cb014d921000bfe3027
+size 5599297376

functionary-small-v3.1-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb18aaee12326ee6d2e781e50858920c5c7442c6e56d88144e0fe21bfe1dac4
+size 6596009824

functionary-small-v3.1-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05072bb72124e4982d13fee0054242a259f68d19d19e7a7ebf1c4cb01c4347f
+size 8540773952

functionary-small-v3.1-tq1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f8f4fe4d9b128c244bda6c7b7e7deff782ae22caafaefbcaa687618950c47d
+size 2207547232

functionary-small-v3.1-tq2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4cb7f7134ea6bb73bf3c751df35b068f20c04e2e9f29e8f291df74a1a107bc
+size 2534702944

functionary-small-v3.1.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d857ff5b306ad413b9fc08fecf1603cb8d4a53ebd17af67c9a0b3398ad3d6c
+size 4988170