初始化项目，由ModelHub XC社区提供模型

Model: Mungert/Arch-Agent-1.5B-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,70 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+ 
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+Arch-Agent-1.5B-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B.imatrix filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Agent-1.5B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Arch-Agent-1.5B-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50ccd10783791387cf288a9676f7a1ee1099e27bd42eeed386678f68ba87290d
+size 3093667040

Arch-Agent-1.5B-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66aeed938dc03ab9d0eca4619d9edaa49f9f74fb56bc3b1aa1b898282dcfc095
+size 2298879200

Arch-Agent-1.5B-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b35141db9f68f8dac899c5c98b3419a954336327102d4b87ee450991850a491
+size 2298879200

Arch-Agent-1.5B-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8e5a74323fd3c2649ea31f73886fb43b9dbc76c1b0132a449828a41d7570aa
+size 774295072

Arch-Agent-1.5B-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72dd88aefd57a97eefcf83249b24124469ce671c43af5e1d0c76e007064b6626
+size 774295072

Arch-Agent-1.5B-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56cb7010ce97fc7590102957ccd758dd6fa210157c2e9f6015d2f5417bd0bf53
+size 707866144

Arch-Agent-1.5B-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7fa5f1108a69768809445f411396b78eef58ce24e807b9a7fd4ce57d143609d
+size 694017568

Arch-Agent-1.5B-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ff19040e40b5161111ac929af004e2663346e4a431e5a6fab95d6a2f99e006
+size 936329248

Arch-Agent-1.5B-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77933e633c78215f45f8c68ef609697a00ccfe141e208d650721e5f3655cca8
+size 895729696

Arch-Agent-1.5B-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5b19b86d0b6bdf3e4049f356b5daf08c421a3769b8d6d22c5ffb68ea87e06d5
+size 820736032

Arch-Agent-1.5B-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b9a8bb26b437eb1893d107bee95df606a45b52f1c7b46dfcd1909c3ffa4168d
+size 789741088

Arch-Agent-1.5B-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6a669b83db5c4a6aded3df320fab96d103fd9dc076925e3096931d1884e31e
+size 874786336

Arch-Agent-1.5B-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951fc58e24d46a27e85ba5b5e7683da2ed29a953beb32981f920e830816b0e09
+size 971259424

Arch-Agent-1.5B-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7121de927cd83abf4d497862be3ebc772cd041a70018a39a6d283ea9730c519
+size 976535584

Arch-Agent-1.5B-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b3a474939004438e6f281fd2d3c7f75cff34d772a596de6921785a23dcdd3b
+size 947388448

Arch-Agent-1.5B-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41589cab7c7b3ef9429db29c3e81d06d391519e0d43b4638044c78bac7adc22b
+size 1067732512

Arch-Agent-1.5B-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8dd22fad7717109515019ae45764439a409b6ce178c6e732a2e6b271832eb86
+size 1164205600

Arch-Agent-1.5B-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8975c3db6e62b1f9409277bcf0ad996a8fc8d50848a18fbf4a46481e89fd1764
+size 1126928416

Arch-Agent-1.5B-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c419b75064464b9ae0a1a92f86e96cd324f7c5ce9b6f03aa7614889b0b4f86a4
+size 1111887904

Arch-Agent-1.5B-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87f8330da6202a9e81f6f6dfe0e20ea7a911c811bcdac2817c9fb2ec40834e3
+size 1272737824

Arch-Agent-1.5B-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2496fb8de8f16268f2909907335635469abd76de8e421d684291f59575d995
+size 1646570720

Arch-Agent-1.5B.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:888a329f58a40a803a5b2608bbde172524e87a4e2da85e5e173000cbb6b543d8
+size 2042248

README.md

@@ -0,0 +1,208 @@
+---
+license: other
+license_name: katanemo-research
+license_link: >-
+  https://huggingface.co/katanemo/Arch-Agent-1.5B/blob/main/LICENSE
+base_model:
+- Qwen/Qwen2.5-Coder-1.5B-Instruct
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# <span style="color: #7FFF7F;">Arch-Agent-1.5B 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 [`0142961a`](https://github.com/ggerganov/llama.cpp/commit/0142961a2e67909e33cdf410274b56c08c5dce7a).
+
+
+
+
+
+
+---
+
+<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-->
+
+
+# katanemo/Arch-Agent-1.5B
+
+## Overview
+Arch-Agent is a collection of state-of-the-art (SOTA) LLMs specifically designed for advanced function calling and agent-based applications. Designed to power sophisticated multi-step and multi-turn workflows, Arch-Agent excels at handling complex, multi-step tasks that require intelligent tool selection, adaptive planning, and seamless integration with external APIs and services. Built with a focus on real-world agent deployments, Arch-Agent delivers leading performance in complex scenarios while maintaining reliability and precision across extended function call sequences. Key capabilities inlcude:
+
+- **Multi-Turn Function Calling**: Maintains contextual continuity across multiple dialogue turns, enabling natural, ongoing conversations with nested or evolving tool use.
+- **Multi-Step Function Calling**: Plans and executes a sequence of function calls to complete complex tasks. Adapts dynamically based on intermediate results and decomposes goals into sub-tasks.
+- **Agentic Capabilities**: Advanced decision-making and workflow management for complex agentic tasks with seamless tool coordination and error recovery.
+
+For more details, including fine-tuning, inference, and deployment, please refer to our [Github](https://github.com/katanemo/Arch-Function).
+
+
+## Performance Benchmarks
+We evaluate Katanemo Arch-Agent series on the [Berkeley Function-Calling Leaderboard (BFCL)](https://gorilla.cs.berkeley.edu/leaderboard.html#leaderboard). We compare with commonly-used models and the results (as of June 14th, 2025) are shown below.
+
+<div align="center">
+  <img width="100%" height="auto" src="./assets/Arch-Agent-1.5B.png"></a>
+</div>
+
+> [!NOTE]
+> For evaluation, we use YaRN scaling to deploy the models for Multi-Turn evaluation, and all Arch-Agent models are evaluated with a context length of 64K.
+
+## Requirements
+The code of Arch-Agent-1.5B has been in the Hugging Face `transformers` library and we recommend to install latest version:
+```bash
+pip install transformers>=4.51.0
+```
+
+
+## How to use
+We use the following example to illustrate how to use our model to perform function calling tasks. Please note that, our model works best with our provided prompt format. It allows us to extract JSON output that is similar to the [OpenAI's function calling](https://platform.openai.com/docs/guides/function-calling).
+
+
+### Quickstart
+````python
+import json
+from typing import Any, Dict, List
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "katanemo/Arch-Agent-1.5B"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+TASK_PROMPT = (
+    "You are a helpful assistant designed to assist with the user query by making one or more function calls if needed."
+    "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\n"
+    "You are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{tool_text}"
+    "\n</tools>\n\nFor each function call, return a json object with function name and arguments within "
+    """<tool_call></tool_call> XML tags:\n<tool_call>\n{{"name": <function-name>, """
+    """"arguments": <args-json-object>}}\n</tool_call>"""
+)
+
+# Define available tools
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get the current weather for a location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "str",
+                        "description": "The city and state, e.g. San Francisco, New York",
+                    },
+                    "unit": {
+                        "type": "str",
+                        "enum": ["celsius", "fahrenheit"],
+                        "description": "The unit of temperature to return",
+                    },
+                },
+                "required": ["location"],
+            },
+        },
+    }
+]
+
+# Helper function to create the system prompt for our model
+def format_prompt(tools: List[Dict[str, Any]]):
+    tool_text = "\n".join(
+        [json.dumps(tool["function"], ensure_ascii=False) for tool in tools]
+    )
+    return TASK_PROMPT.format(tool_text=tool_text)
+
+system_prompt = format_prompt(tools)
+
+messages = [
+    {"role": "system", "content": system_prompt},
+    {"role": "user", "content": "What is the weather in Seattle?"},
+]
+
+model_inputs = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, return_tensors="pt", return_dict=True
+).to(model.device)
+
+generated_ids = model.generate(**model_inputs, max_new_tokens=32768)
+generated_ids = [
+    output_ids[len(input_ids) :]
+    for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+````
+
+# License
+The Arch-Agent collection is distributed under the [Katanemo license](https://huggingface.co/katanemo/Arch-Agent-1.5B/blob/main/LICENSE).
+
+<!--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! 😊

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}