Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,79 @@
+*.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-20b-functioncalling-f16.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling.imatrix filter=lfs diff=lfs merge=lfs -text
+granite-20b-functioncalling-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,188 @@
+---
+license: apache-2.0
+---
+
+# <span style="color: #7FFF7F;">granite-20b-functioncalling GGUF Models</span>
+
+
+## <span style="color: #7F7FFF;">Model Generation Details</span>
+
+This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`0a5a3b5c`](https://github.com/ggerganov/llama.cpp/commit/0a5a3b5cdfd887cf0f8e09d9ff89dee130cfcdde).
+
+
+
+
+
+---
+
+## <span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>
+
+I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.
+
+In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here:  
+👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py)
+
+While this does increase model file size, it significantly improves precision for a given quantization level.
+
+### **I'd love your feedback—have you tried this? How does it perform for you?**
+
+
+
+
+---
+
+<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
+  Click here to get info on choosing the right GGUF model format
+</a>
+
+---
+
+
+
+<!--Begin Original Model Card-->
+
+### Granite-20B-FunctionCalling
+#### Model Summary
+Granite-20B-FunctionCalling is a finetuned model based on IBM's [granite-20b-code-instruct](https://huggingface.co/ibm-granite/granite-20b-code-instruct) model to introduce function calling abilities into Granite model family. The model is trained using a multi-task training approach on seven fundamental tasks encompassed in function calling, those being Nested Function Calling, Function Chaining, Parallel Functions, Function Name Detection, Parameter-Value Pair Detection, Next-Best Function, and Response Generation.
+
+- **Developers**: IBM Research
+- **Paper**: [Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks](https://arxiv.org/pdf/2407.00121v1)
+- **Release Date**: July 9th, 2024
+- **License**: [Apache 2.0.](https://www.apache.org/licenses/LICENSE-2.0)
+
+### Usage
+### Intended use
+The model is designed to respond to function calling related instructions.
+
+### Generation
+This is a simple example of how to use Granite-20B-Code-FunctionCalling model.
+```python
+import json
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+device = "cuda" # or "cpu"
+model_path = "ibm-granite/granite-20b-functioncalling"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+# drop device_map if running on CPU
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
+model.eval()
+
+# define the user query and list of available functions
+query = "What's the current weather in New York?"
+functions = [
+    {
+        "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"]
+        }
+    },
+    {
+        "name": "get_stock_price",
+        "description": "Retrieves the current stock price for a given ticker symbol. The ticker symbol must be a valid symbol for a publicly traded company on a major US stock exchange like NYSE or NASDAQ. The tool will return the latest trade price in USD. It should be used when the user asks about the current or most recent price of a specific stock. It will not provide any other information about the stock or company.",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "ticker": {
+                    "type": "string",
+                    "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
+                }
+            },
+            "required": ["ticker"]
+        }
+    }
+]
+
+
+# serialize functions and define a payload to generate the input template
+payload = {
+    "functions_str": [json.dumps(x) for x in functions],
+    "query": query,
+}
+
+instruction = tokenizer.apply_chat_template(payload, tokenize=False, add_generation_prompt=True)
+
+# tokenize the text
+input_tokens = tokenizer(instruction, return_tensors="pt").to(device)
+
+# generate output tokens
+outputs = model.generate(**input_tokens, max_new_tokens=100)
+
+# decode output tokens into text
+outputs = tokenizer.batch_decode(outputs)
+
+# loop over the batch to print, in this example the batch size is 1
+for output in outputs:
+    # Each function call in the output will be preceded by the token "<function_call>" followed by a 
+    # json serialized function call of the format {"name": $function_name$, "arguments" {$arg_name$: $arg_val$}}
+    # In this specific case, the output will be: <function_call> {"name": "get_current_weather", "arguments": {"location": "New York"}}
+    print(output)
+```
+
+
+<!--End Original Model Card-->
+
+---
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+
+Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:  
+
+👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  
+
+
+The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)
+
+💬 **How to test**:  
+ Choose an **AI assistant type**:  
+   - `TurboLLM` (GPT-4.1-mini)  
+   - `HugLLM` (Hugginface Open-source models)  
+   - `TestLLM` (Experimental CPU-only)  
+
+### **What I’m Testing**  
+I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  
+- **Function calling** against live network services  
+- **How small can a model go** while still handling:  
+  - Automated **Nmap security scans**  
+  - **Quantum-readiness checks**  
+  - **Network Monitoring tasks**  
+
+🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):  
+- ✅ **Zero-configuration setup**  
+- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.
+- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  
+
+### **Other Assistants**  
+🟢 **TurboLLM** – Uses **gpt-4.1-mini** :
+- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. 
+- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
+- **Real-time network diagnostics and monitoring**
+- **Security Audits**
+- **Penetration testing** (Nmap/Metasploit)  
+
+🔵 **HugLLM** – Latest Open-source models:  
+- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
+
+### 💡 **Example commands you could test**:  
+1. `"Give me info on my websites SSL certificate"`  
+2. `"Check if my server is using quantum safe encyption for communication"`  
+3. `"Run a comprehensive security audit on my server"`
+4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution!
+
+### Final Word
+
+I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
+
+If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
+
+I'm also open to job opportunities or sponsorship.
+
+Thank you! 😊

granite-20b-functioncalling-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b584e9aacbaa10ccc5c120615cb59ad08ceb5cd1916cedc53834fa52fb882a0
+size 40243485088

granite-20b-functioncalling-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ffa6ca6df70cd02006de0e7d80d6a1bf2018e921163ff81007b50e5513fa33b
+size 32882481568

granite-20b-functioncalling-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a04df531d2aa5fc30abb6f29bc8f9d96f2e5110635069677d15037433cc54d
+size 32882481568

granite-20b-functioncalling-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:917fa8f93752010e5f883f3561967485d2bdfe2a9214846ef5bb8c5f6c1f63b0
+size 6543375104

granite-20b-functioncalling-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f134e61d6e9fdfb9ea4d2692a9583c72eff849dc0f963cac57a69bf329c734
+size 6070704896

granite-20b-functioncalling-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001755f36013af3110a2abaee85bc50be4d993fe29658df6f78d16663e835c01
+size 7714986752

granite-20b-functioncalling-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad75e6335b25e3657e48b41e2645e7fd72c7b23001c377f4ed50edb91aea467
+size 7469619968

granite-20b-functioncalling-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79c573621f318ed8be4ab961815d9c1b95abbe8152a3228443514a175d41d29
+size 7095450368

granite-20b-functioncalling-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8adb7d5550d16cc7351ce5a901f1c02252e1c0c8995a14ef1f20788d3e16dae
+size 6561438464

granite-20b-functioncalling-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711fb040b47c1b81982197fc9bce204cb6732ccb2c64ffd8970d67731ebdc197
+size 10016971520

granite-20b-functioncalling-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44108e29adcc81f0ca87e4ee203dcceffbab1c7c7d61c76732d84addabf4d09
+size 10016971520

granite-20b-functioncalling-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b6c478620ca0ad06138a2c2beedc4469a830c3acbdd81998aa1942814f678e
+size 8850397952

granite-20b-functioncalling-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ba0250c7612ce170d4348c5818513ebff8bd993b4c8159f8ac2d442a0302b9a
+size 8758385408

granite-20b-functioncalling-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4deaaf9368c97458ce0903017d9cb8de6b6ed97b1a22740ccea9a700edd8cd
+size 11552480000

granite-20b-functioncalling-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3deda9a5fdd3ec2106244db148fb7768f541937aab2e82ed7d056e3bcd1196b8
+size 10936507136

granite-20b-functioncalling-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded972b36da6dc46b04be4adb6d9ed572b22061cd579608f1ad42be8238cf5e1
+size 8066374400

granite-20b-functioncalling-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0eeee84c1d75b69b9537aedb37ae2650b992c94d9277eb48f9e190ca647f7d7
+size 8026266368

granite-20b-functioncalling-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56bc76a6223cd5da5e7b39338f4cf569f89da4f76c5f09b3ee44c3fac1285844
+size 10462485248

granite-20b-functioncalling-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a51970a70aebed68d44a18b0a57d20b713c7012e96298bca210b98eda41766d
+size 10422377216

granite-20b-functioncalling-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab379a68d5477e1afef49ca83ae1760a4876e61c71b15dcfa1f31946f1843b8
+size 11474623232

granite-20b-functioncalling-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879f834fc6f98a5293b6952c71284c6e9fa4681a097660d6ac798f596d95485b
+size 12725443328

granite-20b-functioncalling-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aed03172ce6acb4d2bc04f441b4f1b50c6a457eb89c12ecc131f32c25c433fc
+size 12636183296

granite-20b-functioncalling-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfce2880ae709d1797584d019bbc815c15ba98347bf7efd8a683b31349e8fc2
+size 11894577920

granite-20b-functioncalling-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de4ba80804296c6a1718d1f358d80b7b5e31b773bc65c79b549d9581fbad780
+size 13976263424

granite-20b-functioncalling-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86019c34dd62b32adefc031400053744716d094bc5162234b8267ef9bcf23d22
+size 15227083520

granite-20b-functioncalling-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ccb61503ec1acaa36be2d499c5d5313c34af1531e0bc6310ba0260224a32f66
+size 14869502720

granite-20b-functioncalling-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:847086f6df8fb285b834960694e676902e19781e41a6d805570f423ea50fb983
+size 14379850496

granite-20b-functioncalling-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc3ab8df9c6bcc6f661565506ba300e8e86def82c700eecd8da4aeede73641e
+size 16634256128

granite-20b-functioncalling-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae925efa42e1fa1ea004c50d5dde5462d21c6ec062418c93ae47db0762c8089
+size 21481183648

granite-20b-functioncalling.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ebf9f3438304470886f12e0f4089909de01f52806bac2f0e738ccb125f49ec1
+size 8952830