commit e6cf7cad0ee0cff15287265c5f6410756e3f88e9 Author: ModelHub XC Date: Sun Sep 20 03:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Mungert/LFM2-1.2B-RAG-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0702db4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.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 +LFM2-1.2B-RAG-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG-bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2-1.2B-RAG-bf16.gguf b/LFM2-1.2B-RAG-bf16.gguf new file mode 100644 index 0000000..d3cd241 --- /dev/null +++ b/LFM2-1.2B-RAG-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f64d9858cf2f6e099ad27de450c306f22626072aee6bba6c35b641fbf9bddd +size 2343326144 diff --git a/LFM2-1.2B-RAG-f16_q8_0.gguf b/LFM2-1.2B-RAG-f16_q8_0.gguf new file mode 100644 index 0000000..008cb65 --- /dev/null +++ b/LFM2-1.2B-RAG-f16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b544de125ad7ea9f37812bf84b67fceedaa041772106e53fffebe38ffb5875 +size 1653232064 diff --git a/LFM2-1.2B-RAG-imatrix.gguf b/LFM2-1.2B-RAG-imatrix.gguf new file mode 100644 index 0000000..8f385c5 --- /dev/null +++ b/LFM2-1.2B-RAG-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d932eeab8f9d062bf43b1424e00ca5a413256fe7205803e109ad75a3de72f94 +size 1161536 diff --git a/LFM2-1.2B-RAG-iq3_m.gguf b/LFM2-1.2B-RAG-iq3_m.gguf new file mode 100644 index 0000000..387dbe5 --- /dev/null +++ b/LFM2-1.2B-RAG-iq3_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf6dbc05cda4a7f913bd961a3a897e53de011cbb6e1b3ca513be41124bbb2239 +size 588616416 diff --git a/LFM2-1.2B-RAG-iq3_xs.gguf b/LFM2-1.2B-RAG-iq3_xs.gguf new file mode 100644 index 0000000..c978d05 --- /dev/null +++ b/LFM2-1.2B-RAG-iq3_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49239f5bac3c242cc9684209dd290ad2e0c969097e787bbaf14c0ab45d764b35 +size 544731872 diff --git a/LFM2-1.2B-RAG-iq3_xxs.gguf b/LFM2-1.2B-RAG-iq3_xxs.gguf new file mode 100644 index 0000000..54e5766 --- /dev/null +++ b/LFM2-1.2B-RAG-iq3_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df8de7135281e1c47d45306a3b250b1efa901574de6c6960ac158b9d579e597d +size 528610016 diff --git a/LFM2-1.2B-RAG-iq4_nl.gguf b/LFM2-1.2B-RAG-iq4_nl.gguf new file mode 100644 index 0000000..8860d46 --- /dev/null +++ b/LFM2-1.2B-RAG-iq4_nl.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f233644ef20b0d436427cc9246d0bda2b47a661c6e27ed059aefa35e2746078 +size 661148384 diff --git a/LFM2-1.2B-RAG-iq4_xs.gguf b/LFM2-1.2B-RAG-iq4_xs.gguf new file mode 100644 index 0000000..b333f1f --- /dev/null +++ b/LFM2-1.2B-RAG-iq4_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:416ef64e03ff43665cacede1868c5ea670e20920728cf06b60169d86f7782ede +size 663376608 diff --git a/LFM2-1.2B-RAG-q3_k_m.gguf b/LFM2-1.2B-RAG-q3_k_m.gguf new file mode 100644 index 0000000..582126a --- /dev/null +++ b/LFM2-1.2B-RAG-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee41ea73dcf48e9f401a32e23047886b1bbc71c3a08fb3ed7fb11e574b254341 +size 597332704 diff --git a/LFM2-1.2B-RAG-q3_k_s.gguf b/LFM2-1.2B-RAG-q3_k_s.gguf new file mode 100644 index 0000000..b80289b --- /dev/null +++ b/LFM2-1.2B-RAG-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41955015074134aa5f9292307f8ec0b000129fa2b9ba8e20070ca299b46eb429 +size 579506912 diff --git a/LFM2-1.2B-RAG-q4_0.gguf b/LFM2-1.2B-RAG-q4_0.gguf new file mode 100644 index 0000000..bf02c00 --- /dev/null +++ b/LFM2-1.2B-RAG-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd810bb3cdfbdc464946d0c9ec313be566f25a659032be0d906197ae2db56083 +size 728257248 diff --git a/LFM2-1.2B-RAG-q4_1.gguf b/LFM2-1.2B-RAG-q4_1.gguf new file mode 100644 index 0000000..22974f5 --- /dev/null +++ b/LFM2-1.2B-RAG-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c341ad47fbe5b28b46aaf2b9d369c2464a1e5760caa1509b148dc60ad3166e93 +size 742675168 diff --git a/LFM2-1.2B-RAG-q4_k_m.gguf b/LFM2-1.2B-RAG-q4_k_m.gguf new file mode 100644 index 0000000..40425d1 --- /dev/null +++ b/LFM2-1.2B-RAG-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ecf46e82c7f626ad42c15a287fdac4711d564683d80e176a4477b6fe67e5a2 +size 754873056 diff --git a/LFM2-1.2B-RAG-q4_k_s.gguf b/LFM2-1.2B-RAG-q4_k_s.gguf new file mode 100644 index 0000000..f78d3d2 --- /dev/null +++ b/LFM2-1.2B-RAG-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab0f00e4d2e4fe8eb65072130da511f476d8ccfecb4ced373b086a09fe43dfd +size 705319648 diff --git a/LFM2-1.2B-RAG-q5_0.gguf b/LFM2-1.2B-RAG-q5_0.gguf new file mode 100644 index 0000000..f9c7ef4 --- /dev/null +++ b/LFM2-1.2B-RAG-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b46c237630a75548506abcc6ee2ad1a5fe8b2d2362461edec8d3f3a610619afc +size 857756384 diff --git a/LFM2-1.2B-RAG-q5_1.gguf b/LFM2-1.2B-RAG-q5_1.gguf new file mode 100644 index 0000000..c0f10e4 --- /dev/null +++ b/LFM2-1.2B-RAG-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d8f0932e5cac38dd84d4bd3283d90dc8f84b0d3acfdbae1f1e4ea1a01547214 +size 922505952 diff --git a/LFM2-1.2B-RAG-q5_k_m.gguf b/LFM2-1.2B-RAG-q5_k_m.gguf new file mode 100644 index 0000000..af140fa --- /dev/null +++ b/LFM2-1.2B-RAG-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236a7cc0bd8d1ddfc3150f2edf9b73b532b5d16f45d77d82fbd28451d54e276d +size 876417760 diff --git a/LFM2-1.2B-RAG-q6_k_m.gguf b/LFM2-1.2B-RAG-q6_k_m.gguf new file mode 100644 index 0000000..33bd6e9 --- /dev/null +++ b/LFM2-1.2B-RAG-q6_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f59e8d66b7e2d6fddc7644d85fc579a16326418b8ba4e87fa4936d227cbc4653 +size 995349216 diff --git a/LFM2-1.2B-RAG-q8_0.gguf b/LFM2-1.2B-RAG-q8_0.gguf new file mode 100644 index 0000000..db64c21 --- /dev/null +++ b/LFM2-1.2B-RAG-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:531a01f178f4a865d8d154aa125dc6dfd24cc08cc984904a4bce46f69287a89a +size 1246253504 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9d71931 --- /dev/null +++ b/README.md @@ -0,0 +1,216 @@ +--- +library_name: transformers +license: other +license_name: lfm1.0 +license_link: LICENSE +language: +- en +- ar +- zh +- fr +- de +- ja +- ko +- es +pipeline_tag: text-generation +tags: +- liquid +- lfm2 +- edge +base_model: LiquidAI/LFM2-1.2B +--- + +# LFM2-1.2B-RAG GGUF Models + + +## Model Generation Details + +This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`ee09828cb`](https://github.com/ggerganov/llama.cpp/commit/ee09828cb057460b369576410601a3a09279e23c). + + + + + + +--- + + + Click here to get info on choosing the right GGUF model format + + +--- + + + + + + +
+
+ Liquid AI +
+
+ + + Playground + + + + + + + + + + + + + + + + + + + Leap + + + + + + + + + + + + + + +
+
+ +# LFM2-1.2B-RAG + +Based on [LFM2-1.2B](https://huggingface.co/LiquidAI/LFM2-1.2B), LFM2-1.2B-RAG is specialized in answering questions based on provided contextual documents, for use in RAG (Retrieval-Augmented Generation) systems. + +**Use cases**: + +- Chatbot to ask questions about the documentation of a particular product. +- Custom support with an internal knowledge base to provide grounded answers. +- Academic research assistant with multi-turn conversations about research papers and course materials. + +You can find more information about other task-specific models in this [blog post](https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices). + +## 📄 Model details + +**Generation parameters**: We recommend using greedy decoding with a `temperature=0`. + +**System prompt**: The system prompt is optional. You can force the output's language, for example, using "Always respond in English, regardless of the user's input language." By default, the output's language follows the user prompt's language. + +**Supported languages**: English, Arabic, Chinese, French, German, Japanese, Korean, Portuguese, and Spanish. + +![68d417d4e3a23b976f25091a_Model Library_Prompt + Answer (Medium)_Lightmode](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/Drm8eJpwx_LhNfspEmrNl.png) + +**Training approach**: We fine-tuned the LFM2-1.2B-RAG model on a dataset that includes 1M+ samples of multi-turn interactions and multi-document samples consisting of a mix of curated open source documents as well as generated synthetic ones. + +**Chat template**: LFM2 uses a ChatML-like chat template as follows: + +``` +<|startoftext|><|im_start|>user +Use the following context to answer questions: +Beach soccer differs significantly from its grass-rooted counterpart. [...]<|im_end|> +<|im_start|>assistant +Each team in a beach soccer match consists of five players, including a goalkeeper.{<|im_end|> +``` + +You can automatically apply it using the dedicated [`.apply_chat_template()`](https://huggingface.co/docs/transformers/en/chat_templating#applychattemplate) function from Hugging Face transformers. + +> [!WARNING] +> ⚠️ The model supports both single-turn and multi-turn conversations. + +
+
+ +
+
+ +RAG systems enable AI solutions to include new, up-to-date, and potentially proprietary information in LLM responses that was not present in the training data. When a user asks a question, the retrieval component locates and delivers related documents from a knowledge base, and then the RAG generator model answers the question based on facts from those contextual documents. + +## 🏃 How to run + +- Hugging Face: [LFM2-1.2B](https://huggingface.co/LiquidAI/LFM2-1.2B) +- llama.cpp: [LFM2-1.2B-Extract-GGUF](https://huggingface.co/LiquidAI/LFM2-1.2B-Extract-GGUF) +- LEAP: [LEAP model library](https://leap.liquid.ai/models?model=lfm2-1.2b-extract) + +## 📬 Contact + +If you are interested in custom solutions with edge deployment, please contact [our sales team](https://www.liquid.ai/contact). + + + +--- + +# 🚀 If you find these models useful + +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! 😊