commit 8b43ddb30d861c1f4bb8d687aa598f3b450161e3 Author: ModelHub XC Date: Tue Sep 22 08:31:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Mungert/LFM2-350M-Extract-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f272a6a --- /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 +LFM2-350M-Extract-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Extract-bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2-350M-Extract-bf16.gguf b/LFM2-350M-Extract-bf16.gguf new file mode 100644 index 0000000..cc9f882 --- /dev/null +++ b/LFM2-350M-Extract-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3b7b2225c55242bc258a7cd8f4029601a07254bdae73961eb3b8d5b5693665 +size 711483776 diff --git a/LFM2-350M-Extract-f16_q8_0.gguf b/LFM2-350M-Extract-f16_q8_0.gguf new file mode 100644 index 0000000..e0509bc --- /dev/null +++ b/LFM2-350M-Extract-f16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d00c704b4a8edab52be3df1b24c73aad4ce28b432030e6528c245b81c3a53e7 +size 521757056 diff --git a/LFM2-350M-Extract-imatrix.gguf b/LFM2-350M-Extract-imatrix.gguf new file mode 100644 index 0000000..ce575b8 --- /dev/null +++ b/LFM2-350M-Extract-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8246f2772d7c98fe64d00cd907daec489eee02de6f5f48b72514ad710d2cdf +size 620864 diff --git a/LFM2-350M-Extract-iq3_m.gguf b/LFM2-350M-Extract-iq3_m.gguf new file mode 100644 index 0000000..b30eab0 --- /dev/null +++ b/LFM2-350M-Extract-iq3_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad5a655906575cc1a67357c6a046fa1cf21f0e6deebbb8c50c7b854b9932ec4e +size 189850272 diff --git a/LFM2-350M-Extract-iq3_xs.gguf b/LFM2-350M-Extract-iq3_xs.gguf new file mode 100644 index 0000000..13da345 --- /dev/null +++ b/LFM2-350M-Extract-iq3_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce9681a1d03b803d3619b858cfd93b9cc2deb741cc4abfb12edda28f6fbfa061 +size 177369760 diff --git a/LFM2-350M-Extract-iq3_xxs.gguf b/LFM2-350M-Extract-iq3_xxs.gguf new file mode 100644 index 0000000..4719d73 --- /dev/null +++ b/LFM2-350M-Extract-iq3_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0127cffd5ab662474d6321a2c222d6fe943b702121a1c56c45939ed3c9d7e7d4 +size 173044384 diff --git a/LFM2-350M-Extract-iq4_nl.gguf b/LFM2-350M-Extract-iq4_nl.gguf new file mode 100644 index 0000000..d948cbf --- /dev/null +++ b/LFM2-350M-Extract-iq4_nl.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db0aaa10bb9381534bff7e6b259d51d2382fcc5c137f1903f45580ba5da3975 +size 202007200 diff --git a/LFM2-350M-Extract-iq4_xs.gguf b/LFM2-350M-Extract-iq4_xs.gguf new file mode 100644 index 0000000..994354f --- /dev/null +++ b/LFM2-350M-Extract-iq4_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8786f55f9950c8b4c691bd45d504fc129221ce7d4f5b12c94bef55ce5fbd9cd2 +size 210330272 diff --git a/LFM2-350M-Extract-q3_k_m.gguf b/LFM2-350M-Extract-q3_k_m.gguf new file mode 100644 index 0000000..9ff5664 --- /dev/null +++ b/LFM2-350M-Extract-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb15466a92442e5f729a21ff7f2eb364a34753cc6f01b477061b004324e3616 +size 192266912 diff --git a/LFM2-350M-Extract-q3_k_s.gguf b/LFM2-350M-Extract-q3_k_s.gguf new file mode 100644 index 0000000..be010af --- /dev/null +++ b/LFM2-350M-Extract-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b52a6db30a1dc0da2fd3ea73a6f7cac9fbd17dec28807c3840b5455cf72d02a8 +size 183354016 diff --git a/LFM2-350M-Extract-q4_0.gguf b/LFM2-350M-Extract-q4_0.gguf new file mode 100644 index 0000000..a884ae4 --- /dev/null +++ b/LFM2-350M-Extract-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2c312d174182625a1de4a8031476b05bbdc102b5eef2ffff078da32fa18118 +size 235561632 diff --git a/LFM2-350M-Extract-q4_1.gguf b/LFM2-350M-Extract-q4_1.gguf new file mode 100644 index 0000000..f82d779 --- /dev/null +++ b/LFM2-350M-Extract-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b43c8de79acacabed6118700b285df40ab32db1a9b97395cd44a01a62ff13b77 +size 228352672 diff --git a/LFM2-350M-Extract-q4_k_m.gguf b/LFM2-350M-Extract-q4_k_m.gguf new file mode 100644 index 0000000..2f9f83e --- /dev/null +++ b/LFM2-350M-Extract-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539e1b6b9542f6c907349a1e761e54a7f40d69ec221385782fb68ed275080db5 +size 243118752 diff --git a/LFM2-350M-Extract-q4_k_s.gguf b/LFM2-350M-Extract-q4_k_s.gguf new file mode 100644 index 0000000..5d02e70 --- /dev/null +++ b/LFM2-350M-Extract-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d99e386a2358a28eeb589e93250e2646363ab772caccceb3ac70407a20b4ee9b +size 222126752 diff --git a/LFM2-350M-Extract-q5_0.gguf b/LFM2-350M-Extract-q5_0.gguf new file mode 100644 index 0000000..a6fd4fb --- /dev/null +++ b/LFM2-350M-Extract-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da7a363024a00d97dfb86ae45e7d98d5ad7590b4369b55ff43eddea41db0e3d9 +size 271475360 diff --git a/LFM2-350M-Extract-q5_1.gguf b/LFM2-350M-Extract-q5_1.gguf new file mode 100644 index 0000000..440e896 --- /dev/null +++ b/LFM2-350M-Extract-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f587210970acd3fa7b6edfb2ce21863983841d1de2b3fa73e744e9952d81d5c2 +size 289432224 diff --git a/LFM2-350M-Extract-q5_k_m.gguf b/LFM2-350M-Extract-q5_k_m.gguf new file mode 100644 index 0000000..49b6258 --- /dev/null +++ b/LFM2-350M-Extract-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c61976fd88f24351b20160587a79bf99dd91b45ecdda2a09f4d45187cc0777 +size 276767392 diff --git a/LFM2-350M-Extract-q6_k_m.gguf b/LFM2-350M-Extract-q6_k_m.gguf new file mode 100644 index 0000000..7867139 --- /dev/null +++ b/LFM2-350M-Extract-q6_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d982584eb47b228b78359771b8f8a8d7d1e14499d7139c41f6ce0026d246ff58 +size 309633696 diff --git a/LFM2-350M-Extract-q8_0.gguf b/LFM2-350M-Extract-q8_0.gguf new file mode 100644 index 0000000..d6c248f --- /dev/null +++ b/LFM2-350M-Extract-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6609dda376e25b015beb3c1c66f6aee7b9690a674267cbba15b79f675ec77fb1 +size 379216256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d01141d --- /dev/null +++ b/README.md @@ -0,0 +1,225 @@ +--- +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/LFM2-350M +--- + +# LFM2-350M-Extract GGUF Models + + +## Model Generation Details + +This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`c8dedc99`](https://github.com/ggerganov/llama.cpp/commit/c8dedc9999eccf7821a9fe5b29f10e8d075e2217). + + + + + + +--- + + + Click here to get info on choosing the right GGUF model format + + +--- + + + + + + +
+
+ Liquid AI +
+
+ + + Playground + + + + + + + + + + + + + + + + + + + Leap + + + + + + + + + + + + + + +
+
+ +# LFM2-350M-Extract + +Based on [LFM2-350M](https://huggingface.co/LiquidAI/LFM2-350M), LFM2-350M-Extract is designed to **extract important information from a wide variety of unstructured documents** (such as articles, transcripts, or reports) into structured outputs like JSON, XML, or YAML. + +**Use cases**: + +- Extracting invoice details from emails into structured JSON. +- Converting regulatory filings into XML for compliance systems. +- Transforming customer support tickets into YAML for analytics pipelines. +- Populating knowledge graphs with entities and attributes from unstructured reports. + +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 strongly recommend using greedy decoding with a `temperature=0`. + +**System prompt**: If no system prompt is provided, the model will default to JSON outputs. We recommend providing a system prompt with a specific format (JSON, XML, or YAML) and a given schema to improve accuracy (see the following example). + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/MeSOLz1XeTtinRjrVkF7d.png) + +**Supported languages**: English, Arabic, Chinese, French, German, Japanese, Korean, Portuguese, and Spanish. + +**Chat template**: LFM2 uses a ChatML-like chat template as follows: + +``` +<|startoftext|><|im_start|>system +Return data as a JSON object with the following schema:\n[...]<|im_end|> +<|im_start|>user +Caenorhabditis elegans is a free-living transparent nematode about 1 mm in length that lives in temperate soil environments.<|im_end|> +<|im_start|>assistant +{ +"species": "C. elegans", +"genus": "Caenorhabditis", +"description": "A free-living transparent nematode about 1 mm in length that lives in temperate soil environments.", +[...]{<|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 is intended for single-turn conversations. + +The data used for training these models was primarily synthetic, which allowed us to ensure a diverse data mix. We used a range of document types, domains, styles, lengths, and languages. We also varied the density and distribution of relevant text in the documents. In some cases, the extracted information was clustered in one part of the document; in others, it’s spread throughout. We applied the same approach of ensuring diversity when creating synthetic user requests and designing the structure of the model outputs. The data generation process underwent many iterations, incorporating ideas and feedback from across the Liquid AI team. + +## 📈 Performance + +We evaluated LFM2-Extract on a dataset of 5,000 documents, covering over 100 topics with a mix of writing styles, ambiguities, and formats. We used a combination of five metrics to capture a balanced view on syntax, accuracy, and faithfulness: + +- **Syntax score**: Checks whether outputs parse cleanly as valid JSON, XML, or YAML. +- **Format accuracy**: Verifies that outputs match the requested format (e.g., JSON when JSON is requested). +- **Keyword faithfulness**: Measures whether values in the structured output actually appear in the input text. +- **Absolute scoring**: A judge LLM scores quality on a 1-5 scale, assessing completeness and correctness of extractions. +- **Relative scoring**: We ask a judge LLM to choose the best answer between the extraction model’s output and the ground-truth answer. + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/DNZgCKMFSg5xhHoBgJjeC.png) + +LFM2-350M-Extract outperforms Gemma 3 4B at this task, a model more than 11x its size. + +## 🏃 How to run + +- Hugging Face: [LFM2-350M](https://huggingface.co/LiquidAI/LFM2-350M) +- llama.cpp: [LFM2-350M-Extract-GGUF](https://huggingface.co/LiquidAI/LFM2-350M-Extract-GGUF) +- LEAP: [LEAP model library](https://leap.liquid.ai/models?model=lfm2-350M-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! 😊