Super-squash history to reclaim storage

.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
+*.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
+Arch-Router-1.5B-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B.imatrix filter=lfs diff=lfs merge=lfs -text
+Arch-Router-1.5B-bf16.gguf filter=lfs diff=lfs merge=lfs -text

Arch-Router-1.5B-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c0f90778339deaf2b92d767cee21ac5577e4a6bb34cc56c38493306622303d1
+size 3093669568

Arch-Router-1.5B-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e592a9c431abe1479117076cc33a36f2c6fc34908de3bd0b78c4066cab0092
+size 2298881728

Arch-Router-1.5B-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e366a357dc26687886bd1ff96f5c74f57b2fe21abd19a8dd862432ea6ceca171
+size 2298881728

Arch-Router-1.5B-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62cec04eca19e590b4bbce01c2e29c829010e7c802ace024bc8b3770991f791f
+size 774297600

Arch-Router-1.5B-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bf1ad330e81fedaa172e897d23bf6767c4d0709c4b27d6fd2c64549a165918
+size 774297600

Arch-Router-1.5B-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a4a09fa54d5da21ef3e8dcc5aee14ff705cb9cea315887ff52fbbdec13e896
+size 707868672

Arch-Router-1.5B-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccddac88eee5b42ce493abe2f6e76e444dd31cb9cbc568483c5829441e739bb
+size 694020096

Arch-Router-1.5B-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba28a80f4cd15ccb932f079f96762ef62443bc21d43c209df2581f7b73442ba
+size 936331776

Arch-Router-1.5B-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c3303020c456013f660aecf2190e9495b7f47300783e5fa6ccacf6b7b7987a
+size 895732224

Arch-Router-1.5B-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e51ac5ccd1d3dd0518bcd3a2765717072105042802a4a3f77b232fa7f1c114
+size 820738560

Arch-Router-1.5B-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2b39264915b2d98367cea2a7a59130590e9165bd11077ca92486c35258c7ae
+size 789743616

Arch-Router-1.5B-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee65727ace1ef919a87dc65562ad18488214369b0088ee967b7f35d1e82d6a43
+size 874788864

Arch-Router-1.5B-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a36ea395fda2e8bebc3072aff001377ff749dd9e4d490262e53c8a64e788b4a
+size 971261952

Arch-Router-1.5B-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b45e35c2d719a49ab51b537dc83382e929aea28b17ce9f5e43bf924811645c
+size 976538112

Arch-Router-1.5B-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a859a7d585c48f559c322094f636d80ffdd0740497492660b068dd87e81423
+size 947390976

Arch-Router-1.5B-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308074208b6bbf93bb596556dd1da7a1a77b6762ccc555813793b9131e7ab0e8
+size 1067735040

Arch-Router-1.5B-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4d087d85290f8c3a9ba3f24970726f4b6e48b06b5ffdfd2a02e1e44848383b
+size 1164208128

Arch-Router-1.5B-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3a9bf5bc142eceee3a52a90d13fc374fdefd985a7e70ea55beb8a811c5ab94
+size 1126930944

Arch-Router-1.5B-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f67297f83aa1c6e7686b8b4be9d259f0edc775b7a710eba05d2f00b51f55576b
+size 1111890432

Arch-Router-1.5B-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7794c866e59c7ed7984206150012175ffa638d5b9a162a7230e757348dc32f
+size 1272740352

Arch-Router-1.5B-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5a718e29a469148ff5ebe35a0a0c235325bc6874ce976fd9941f33fbb2b301
+size 1646573248

Arch-Router-1.5B.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377bba15394086c2216a2fec3b05329908bbb8f1ab1fffa6ac703cfed6667346
+size 2042248

README.md

@@ -0,0 +1,255 @@
+---
+license: other
+license_name: katanemo-research
+license_link: >-
+  https://huggingface.co/katanemo/Arch-Router-1.5B/blob/main/LICENSE
+base_model:
+- Qwen/Qwen2.5-1.5B-Instruct
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+  - routing
+  - preference
+  - arxiv:2506.16655
+  - llm
+paper: https://arxiv.org/abs/2506.16655
+---
+
+# <span style="color: #7FFF7F;">Arch-Router-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 [`73e53dc8`](https://github.com/ggerganov/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277).
+
+
+
+
+
+
+---
+
+<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-Router-1.5B
+
+## Overview
+With the rapid proliferation of large language models (LLMs) -- each optimized for different strengths, style, or latency/cost profile -- routing has become an essential technique to operationalize the use of different models. However, existing LLM routing approaches are limited in two key ways: they evaluate performance using benchmarks that often fail to capture human preferences driven by subjective evaluation criteria, and they typically select from a limited pool of models. 
+
+We introduce a preference-aligned routing framework that guides model selection by matching queries to user-defined domains (e.g., travel) or action types (e.g., image editing) -- offering a practical mechanism to encode preferences in routing decisions. Specifically, we introduce Arch-Router, a compact 1.5B model that learns to map queries to domain-action preferences for model routing decisions. Experiments on conversational datasets demonstrate that our approach achieves state-of-the-art (SOTA) results in matching queries with human preferences, outperforming top proprietary models. 
+
+This model is described in the paper: https://arxiv.org/abs/2506.16655, and powers [Arch](https://github.com/katanemo/arch) the open-source AI-native proxy for agents to enable preference-based routing in a seamless way.
+
+### How It Works
+
+To support effective routing, Arch-Router introduces two key concepts:
+- **Domain** – the high-level thematic category or subject matter of a request (e.g., legal, healthcare, programming).
+- **Action** – the specific type of operation the user wants performed (e.g., summarization, code generation, booking appointment, translation).
+
+Both domain and action configs are associated with preferred models or model variants. At inference time, Arch-Router analyzes the incoming prompt to infer its domain and action using semantic similarity, task indicators, and contextual cues. It then applies the user-defined routing preferences to select the model best suited to handle the request.
+
+### Key Features
+
+- **Structured Preference Routing**: Aligns prompt request with model strengths using explicit domain–action mappings.
+- **Transparent and Controllable**: Makes routing decisions transparent and configurable, empowering users to customize system behavior.
+- **Flexible and Adaptive**: Supports evolving user needs, model updates, and new domains/actions without retraining the router.
+- **Production-Ready Performance**: Optimized for low-latency, high-throughput applications in multi-model environments.
+
+# Requirements
+The code of Arch-Router-1.5B has been in the Hugging Face `transformers` library and we advise you to install latest version:
+```bash
+pip install transformers>=4.37.0
+```
+
+
+# How to use
+We use the following example to illustrate how to use our model to perform routing tasks. Please note that, our model works best with our provided prompt format. 
+### Quickstart
+````python
+import json
+from typing import Any, Dict, List
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "katanemo/Arch-Router-1.5B"
+model = AutoModelForCausalLM.from_pretrained(
+    model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Please use our provided prompt for best performance
+TASK_INSTRUCTION = """
+You are a helpful assistant designed to find the best suited route.
+You are provided with route description within <routes></routes> XML tags:
+<routes>
+\n{routes}\n
+</routes>
+
+<conversation>
+\n{conversation}\n
+</conversation>
+"""
+
+FORMAT_PROMPT = """
+Your task is to decide which route is best suit with user intent on the conversation in <conversation></conversation> XML tags.  Follow the instruction:
+1. If the latest intent from user is irrelevant or user intent is full filled, response with other route {"route": "other"}.
+2. You must analyze the route descriptions and find the best match route for user latest intent. 
+3. You only response the name of the route that best matches the user's request, use the exact name in the <routes></routes>.
+
+Based on your analysis, provide your response in the following JSON formats if you decide to match any route:
+{"route": "route_name"} 
+"""
+
+
+# Define route config
+route_config = [
+    {
+        "name": "code_generation",
+        "description": "Generating new code snippets, functions, or boilerplate based on user prompts or requirements",
+    },
+    {
+        "name": "bug_fixing",
+        "description": "Identifying and fixing errors or bugs in the provided code across different programming languages",
+    },
+    {
+        "name": "performance_optimization",
+        "description": "Suggesting improvements to make code more efficient, readable, or scalable",
+    },
+    {
+        "name": "api_help",
+        "description": "Assisting with understanding or integrating external APIs and libraries",
+    },
+    {
+        "name": "programming",
+        "description": "Answering general programming questions, theory, or best practices",
+    },
+]
+
+
+# Helper function to create the system prompt for our model
+def format_prompt(
+    route_config: List[Dict[str, Any]], conversation: List[Dict[str, Any]]
+):
+    return (
+        TASK_INSTRUCTION.format(
+            routes=json.dumps(route_config), conversation=json.dumps(conversation)
+        )
+        + FORMAT_PROMPT
+    )
+
+
+# Define conversations
+
+conversation = [
+    {
+        "role": "user",
+        "content": "fix this module 'torch.utils._pytree' has no attribute 'register_pytree_node'. did you mean: '_register_pytree_node'?",
+    }
+]
+
+route_prompt = format_prompt(route_config, conversation)
+
+messages = [
+    {"role": "user", "content": route_prompt},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, return_tensors="pt"
+).to(model.device)
+
+# 2. Generate
+generated_ids = model.generate(
+    input_ids=input_ids,  # or just positional: model.generate(input_ids, …)
+    max_new_tokens=32768,
+)
+
+# 3. Strip the prompt from each sequence
+prompt_lengths = input_ids.shape[1]  # same length for every row here
+generated_only = [
+    output_ids[prompt_lengths:]  # slice off the prompt tokens
+    for output_ids in generated_ids
+]
+
+# 4. Decode if you want text
+response = tokenizer.batch_decode(generated_only, skip_special_tokens=True)[0]
+print(response)
+````
+
+Then you should be able to see the following output string in JSON format:
+````python
+{"route": "bug_fixing"}
+````
+
+To better understand how to create the route descriptions, please take a look at our [Katanemo API](https://docs.archgw.com/guides/llm_router.html).
+
+# License
+Katanemo Arch-Router model is distributed under the [Katanemo license](https://huggingface.co/katanemo/Arch-Router-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! 😊