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

AceInstruct-1.5B-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eecbc48a9a1042b64b068d68db37242becfaafe02db1e114b50f4751ac088ee
+size 3560414432

AceInstruct-1.5B-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef5b559e80c7516d399a88ca50a4f76d088bc31d7707d67660f49f63db2d0ad
+size 2765626592

AceInstruct-1.5B-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55a431dce443632a3ccd034db430af76905f9f6d9842babf37455c57f219e7d
+size 2765626592

AceInstruct-1.5B-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0233b3055fffa4e266cedf7b3171d4cc4b7027434bc5631f27018abeb2d9ac79
+size 934739424

AceInstruct-1.5B-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d94326513e789a49ec1c7386c9d7a989cc178cdd32f82a494b5667aab8ffd45
+size 934739424

AceInstruct-1.5B-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd20066467cc1e67cea752d2615082aafdda8ebaa828abd6a458d61d7f410259
+size 868310496

AceInstruct-1.5B-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:300880b264934c6d69e5854373a1bc0fb6d2d7e962fe7120cddbc9f62197e808
+size 854461920

AceInstruct-1.5B-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d5329febf3ce4fc9c17df4087c47834eb280c382350b845dc31c5eacc341cb2
+size 1067601888

AceInstruct-1.5B-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03f05234a4c4313a0897205b392486df759e01f7aa6efc26024c9eaef80b9ce
+size 1019709408

AceInstruct-1.5B-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec4c2d0453f81ce3c2e3786cd0984dace92d3a217cc9d61f9123f6006b4e53f
+size 1012175328

AceInstruct-1.5B-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8736f9d1e105684c6ffdebb9dc7cabf04f46b76417f1d1c1f5209c6e7fadb91
+size 950185440

AceInstruct-1.5B-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243cdc200c4bb3a2bc7b0089180db2a6a4b861d49c5c98b3b04c571eae1244be
+size 1006058976

AceInstruct-1.5B-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84dfe29c35b36dff12238563f18e5d93797c19d3e96f9a90096df3758fa308a7
+size 1117117920

AceInstruct-1.5B-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ceef6440c4ca1afbe65f9c88cf4e6996d4a2cb83c65a3268f801278f10a366
+size 1167974880

AceInstruct-1.5B-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7e2044e7782f50f640ce5ef203179be1f29eded917c0be49a6dcc88880e7e8
+size 1138827744

AceInstruct-1.5B-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3c08de15001618290230466961777484f426efb3c10264ef63b9553e8d3bc3
+size 1228176864

AceInstruct-1.5B-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c97df87109130c8dabe1e2318ba65f9104373bd0fd629acb466fdb46d0fc69
+size 1339235808

AceInstruct-1.5B-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34de0864b963d6ab0862d24bb247e40ca3acab428944c8473441eaee2cb150a
+size 1318367712

AceInstruct-1.5B-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0bf69c909c7b517f870f71f4493990dc51e73473da3c9ca393c7741d4593da
+size 1303327200

AceInstruct-1.5B-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d53ef96f4976c87963483ea5f38ce537e1dcec01c17560d933278322b4db4e4
+size 1464177120

AceInstruct-1.5B-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18058e3b63bd037028e37333b0e1a66ce60ae8b349f28f8a10d780b95d71c4c3
+size 1894530272

AceInstruct-1.5B.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86446600001279a2499bc643cbbe7309fb9a9d4e6e4159527d80fd7e8e403863
+size 2042214

README.md

@@ -0,0 +1,182 @@
+---
+license: cc-by-nc-4.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- nvidia
+- AceInstruct
+- code
+- math
+- general_domain
+- instruct_model
+- pytorch
+---
+
+# <span style="color: #7FFF7F;">AceInstruct-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 [`b9c3eefd`](https://github.com/ggerganov/llama.cpp/commit/b9c3eefde1b67104bd993485ff38dd62abe9d70c).
+
+
+
+
+
+
+---
+
+<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-->
+
+
+## Introduction
+We introduce AceInstruct, a family of advanced SFT models for coding, mathematics, and general-purpose tasks. The AceInstruct family, which includes AceInstruct-1.5B, 7B, and 72B, is <b>Improved using Qwen</b>. 
+These models are fine-tuned on Qwen2.5-Base using [general SFT datasets](https://huggingface.co/datasets/nvidia/AceMath-Instruct-Training-Data). These same datasets are also used in the training of [AceMath-Instruct](https://huggingface.co/nvidia/AceMath-72B-Instruct). Different from AceMath-Instruct which is specialized for math questions, AceInstruct is versatile and can be applied to a wide range of domains. Benchmark evaluations across coding, mathematics, and general knowledge tasks demonstrate that AceInstruct delivers performance comparable to Qwen2.5-Instruct.
+
+For more information about AceInstruct, check our [website](https://research.nvidia.com/labs/adlr/acemath/) and [paper](https://arxiv.org/abs/2412.15084).
+
+
+## Benchmark Results
+| | Qwen2.5-1.5B-Instruct | AceInstruct-1.5B | Qwen2.5-7B-Instruct | AceInstruct-7B | Qwen2.5-72B-Instruct | AceInstruct-72B | 
+| --------- |:-----:|:-----:|:-----:|:-----:|:-----:|:-----:|
+| HumanEval | 61.60 | 73.17 | 84.80 | 85.37 | 86.60 | 89.63 | 
+| MBPP      | 63.20 | 65.76 | 79.20 | 74.32 | 88.20 | 83.66 |
+| GSM8K     | 73.20 | 80.44 | 91.60 | 93.10 | 95.80 | 96.36 |
+| MATH      | 55.20 | 60.34 | 75.50 | 76.40 | 83.10 | 84.50 |
+| MMLU      | 58.37 | 58.17 | 74.51 | 74.68 | 84.67 | 83.88 |
+| MMLU Pro  | 32.40 | 33.78 | 56.30 | 54.50 | 71.10 | 66.10 |
+| Average   | 57.33 | 61.94 | 76.99 | 76.40 | 84.91 | 84.02 |
+
+We compare AceInstruct to Qwen2.5-Instruct across coding, mathematics, and general knowledge tasks. We find that AceInstruct-1.5B outperforms Qwen2.5-1.5B-Instruct (61.94 vs. 57.33), while AceInstruct-7B and AceInstruct-72B perform similarly to Qwen2.5-7B-Instruct and Qwen2.5-72B-Instruct.
+
+
+## All Resources
+### AceMath Instruction Models
+- [AceMath-1.5B-Instruct](https://huggingface.co/nvidia/AceMath-1.5B-Instruct), [AceMath-7B-Instruct](https://huggingface.co/nvidia/AceMath-7B-Instruct), [AceMath-72B-Instruct](https://huggingface.co/nvidia/AceMath-72B-Instruct)
+
+### AceMath Reward Models
+- [AceMath-7B-RM](https://huggingface.co/nvidia/AceMath-7B-RM), [AceMath-72B-RM](https://huggingface.co/nvidia/AceMath-72B-RM)
+
+### Evaluation & Training Data
+- [AceMath-RewardBench](https://huggingface.co/datasets/nvidia/AceMath-RewardBench), [AceMath-Instruct Training Data](https://huggingface.co/datasets/nvidia/AceMath-Instruct-Training-Data), [AceMath-RM Training Data](https://huggingface.co/datasets/nvidia/AceMath-RM-Training-Data)
+
+### General Instruction Models
+- [AceInstruct-1.5B](https://huggingface.co/nvidia/AceInstruct-1.5B), [AceInstruct-7B](https://huggingface.co/nvidia/AceInstruct-7B), [AceInstruct-72B](https://huggingface.co/nvidia/AceInstruct-72B)
+
+
+## How to use
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "AceInstruct-1.5B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
+
+prompt = "Tell me something about artificial intelligence."
+messages = [{"role": "user", "content": prompt}]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to("cuda")
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=1024
+)
+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]
+```
+
+
+## Correspondence to
+Zihan Liu (zihanl@nvidia.com), Yang Chen (yachen@nvidia.com), Wei Ping (wping@nvidia.com)
+
+
+## Citation
+If you find our work helpful, we’d appreciate it if you could cite us.
+<pre>
+@article{acemath2024,
+  title={AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling},
+  author={Liu, Zihan and Chen, Yang and Shoeybi, Mohammad and Catanzaro, Bryan and Ping, Wei},
+  journal={arXiv preprint},
+  year={2024}
+}
+</pre>
+
+
+## License
+All models in the AceInstruct family are for non-commercial use only, subject to [Terms of Use](https://openai.com/policies/row-terms-of-use/) of the data generated by OpenAI. We put the AceInstruct models under the license of [Creative Commons Attribution: Non-Commercial 4.0 International](https://spdx.org/licenses/CC-BY-NC-4.0).
+
+<!--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! 😊