commit 32b288f23361f89bc901e4f67c60c24c4a42fc70 Author: ModelHub XC Date: Thu Oct 22 01:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Mungert/mem-agent-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..da5f959 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +mem-agent-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q4_1.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent-bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..88a9ade --- /dev/null +++ b/README.md @@ -0,0 +1,208 @@ +--- +pipeline_tag: text-generation +library_name: transformers +--- + +# mem-agent GGUF Models + + +## Model Generation Details + +This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`1d0125bc`](https://github.com/ggerganov/llama.cpp/commit/1d0125bcf1cbd7195ad0faf826a20bc7cec7d3f4). + + + + + +--- + +## Quantization Beyond the IMatrix + +I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides. + +In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here: +👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py) + +While this does increase model file size, it significantly improves precision for a given quantization level. + +### **I'd love your feedback—have you tried this? How does it perform for you?** + + + + +--- + + + Click here to get info on choosing the right GGUF model format + + +--- + + + + + +# mem-agent + +Based on [Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507), this model was trained using GSPO (Zheng et al., 2025) over an agent scaffold that is built around an Obisidian-like memory system and the tools required to interact with it. The model was trained on the following subtasks: +- Retrieval: Retrieving relevant information when needed from the memory system. In this subtask, we also trained the model on filtering the retrieved information and/or obfuscating it completely. +- Updating: Updating the memory system with new information. +- Clarification: Asking for clarification when the user query is not clear/contradicting with the information in the memory system. + +The tools in the scaffold are: +```markdown +# File Operations +create_file(file_path: str, content: str = "") -> bool # Auto-creates parent directories +update_file(file_path: str, old_content: str, new_content: str) -> Union[bool, str] # Returns True or error message +read_file(file_path: str) -> str +delete_file(file_path: str) -> bool +check_if_file_exists(file_path: str) -> bool + +# Directory Operations +create_dir(dir_path: str) -> bool +list_files() -> str # Shows tree structure of current working directory +check_if_dir_exists(dir_path: str) -> bool + +# Utilities +get_size(file_or_dir_path: str) -> int # Bytes; empty = total memory size +go_to_link(link_string: str) -> bool +``` + +In the scaffold, the model uses ``, `` and `` tags to structure its response. Using `` only when it's done interacting with the memory. The `` block is executed in a sandbox with the tools and the results of the code block are returned in a `` tag to the model, forming the agentic loop. + +The model is also trained to be able to handle optional filters given by the user in between tags after the user query. These filters are used to filter the retrieved information and/or obfuscate it completely. + + +## Benchmark + +We evaluated this model and a few other open & closed ones on our benchmark, **md-memory-bench**. We used o3 from OpenAI as the judge. All the other models except driaforall/mem-agent and Qwen/Qwen3-4B-Thinking-2507 were used through OpenRouter.s + +| Model | Retrieval | Update | Clarification | Filter | Overall | +|-------|-----------|--------|---------------|--------|---------| +| qwen/qwen3-235b-a22b-thinking-2507 | 0.9091 | 0.6363 | 0.4545 | 1 | 0.7857 | +| driaforall/mem-agent | 0.8636 | 0.7272 | 0.3636 | 0.9167 | 0.75 | +| z-ai/glm-4.5 | 0.7727 | 0.8181 | 0.3636 | 0.9167 | 0.7321 | +| deepseek/deepseek-chat-v3.1 | 0.6818 | 0.5454 | 0.5454 | 0.8333 | 0.6607 | +| google/gemini-2.5-pro | 0.7273 | 0.4545 | 0.2727 | 1 | 0.6429 | +| google/gemini-2.5-flash | 0.7727 | 0.3636 | 0.2727 | 0.9167 | 0.625 | +| openai/gpt-5 | 0.6818 | 0.5454 | 0.2727 | 0.9167 | 0.625 | +| anthropic/claude-opus-4.1 | 0.6818 | 0 | 0.8181 | 0.5833 | 0.5536 | +| Qwen/Qwen3-4B-Thinking-2507 | 0.4545 | 0 | 0.2727 | 0.75 | 0.3929 | +| moonshotai/kimi-k2 | 0.3181 | 0.2727 | 0.1818 | 0.6667 | 0.3571 | + +Our model, with only 4B parameters, is only second on the benchmark, beating all the open & closed models except for qwen/qwen3-235b-a22b-thinking-2507. The model achieves an overall score of 0.75, a significant improvement over the 0.3929 of the base Qwen model. + +## Usage + +The model, while can be used on its own, is recommended to be used as an MCP server to a bigger model, which can then be used to interact with the memory system. For this, you can check [our repo](https://github.com/firstbatchxyz/mem-agent-mcp/), which contains instructions for both an MCP setup and a cli standalone model usage. + +### Memory + +The model uses a markdown based memory system with links, inspired by Obsidian. The general structure of the memory is: +``` +memory/ + ├── user.md + └── entities/ + └── [entity_name_1].md + └── [entity_name_2].md + └── ... +``` + +- `user.md` is the main file that contains information about the user and their relationships, accompanied by links to the enity file in the format of `[[entities/[entity_name].md]]` per relationship. The link format should be followed strictly. +- `entities/` is the directory that contains the entity files. +- Each entity file follows the same structure as `user.md`. +- Modifying the memory manually does not require restarting the MCP server. + +### Example user.md + +```markdown +# User Information +- user_name: John Doe +- birth_date: 1990-01-01 +- birth_location: New York, USA +- living_location: Enschede, Netherlands +- zodiac_sign: Aquarius + +## User Relationships +- company: [[entities/acme_corp.md]] +- mother: [[entities/jane_doe.md]] +``` + +### Example entity files (jane_doe.md and acme_corp.md) + +```markdown +# Jane Doe +- relationship: Mother +- birth_date: 1965-01-01 +- birth_location: New York, USA +``` + +```markdown +# Acme Corporation +- industry: Software Development +- location: Enschede, Netherlands +``` + +The model is trained on this memory standard and any fruitful use should be on a memory system that follows this standard. We have a few memory export tools for different sources like ChatGPT, Notion, etc. in our mcp server repo. + +## References: +- [GSPO](https://arxiv.org/pdf/2507.18071), Zheng et al., 2025 + + + +--- + +# 🚀 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! 😊 diff --git a/mem-agent-bf16.gguf b/mem-agent-bf16.gguf new file mode 100644 index 0000000..256b818 --- /dev/null +++ b/mem-agent-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def167809008e582ab8830a298adc9e7413200acf40296705ad9d4edfcef8840 +size 8051284800 diff --git a/mem-agent-bf16_q8_0.gguf b/mem-agent-bf16_q8_0.gguf new file mode 100644 index 0000000..80c42da --- /dev/null +++ b/mem-agent-bf16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c1fadc332ab913fe9875a9d85b771732f78d2c85c94088abaffadb0cb22c75 +size 5927918400 diff --git a/mem-agent-f16_q8_0.gguf b/mem-agent-f16_q8_0.gguf new file mode 100644 index 0000000..d3191f6 --- /dev/null +++ b/mem-agent-f16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1592db4a49a5561aee098730041abea2094bfb9db222bd4b9db33047c2a8626 +size 5927918400 diff --git a/mem-agent-imatrix.gguf b/mem-agent-imatrix.gguf new file mode 100644 index 0000000..24d95b4 --- /dev/null +++ b/mem-agent-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc75428bccd61d1b1170cb9731556b61a9b1b7cd853c234c76eb944445e96808 +size 3872672 diff --git a/mem-agent-iq1_m.gguf b/mem-agent-iq1_m.gguf new file mode 100644 index 0000000..b20424d --- /dev/null +++ b/mem-agent-iq1_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed6e410fbefd389dfebe3f005f1e43baf7b7590202c2549b6c0a32122e90950e +size 1219825280 diff --git a/mem-agent-iq1_s.gguf b/mem-agent-iq1_s.gguf new file mode 100644 index 0000000..35afead --- /dev/null +++ b/mem-agent-iq1_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e37a7c7f8f1b6fa3d4bbfb0a0105ac26ca7c1ebe22cc7250fbea91149fddea +size 1129590400 diff --git a/mem-agent-iq2_m.gguf b/mem-agent-iq2_m.gguf new file mode 100644 index 0000000..58b8abb --- /dev/null +++ b/mem-agent-iq2_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:162a76da0f57a6ed5c8ab5d6b996839dd08ced46824d631aafc5845d131d63c9 +size 1507126400 diff --git a/mem-agent-iq2_s.gguf b/mem-agent-iq2_s.gguf new file mode 100644 index 0000000..86183a9 --- /dev/null +++ b/mem-agent-iq2_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60dbeac63096b7086f33facf0bb9d8755ccfa14c2017c8a78e159395201485b +size 1442901120 diff --git a/mem-agent-iq2_xs.gguf b/mem-agent-iq2_xs.gguf new file mode 100644 index 0000000..fda5229 --- /dev/null +++ b/mem-agent-iq2_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a991d105174ec5d30b40254e46501de46981c574f17c22a8826a74ec2f78ed1 +size 1397558400 diff --git a/mem-agent-iq2_xxs.gguf b/mem-agent-iq2_xxs.gguf new file mode 100644 index 0000000..593ed87 --- /dev/null +++ b/mem-agent-iq2_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:636506a206fe55976ff46f88b48cf477a10d76d3ca40036d0c066c16079920c5 +size 1293315200 diff --git a/mem-agent-iq3_m.gguf b/mem-agent-iq3_m.gguf new file mode 100644 index 0000000..ca2b6d8 --- /dev/null +++ b/mem-agent-iq3_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9843a379ac15ed3db7dc430797e47331e1534645e2b24ddf82586944cce57c60 +size 1951378560 diff --git a/mem-agent-iq3_xxs.gguf b/mem-agent-iq3_xxs.gguf new file mode 100644 index 0000000..8a84944 --- /dev/null +++ b/mem-agent-iq3_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddefb7ab118d1cdb348b774f14bee68a91b8923ba5c2aa9178b677d136d4747a +size 1722043520 diff --git a/mem-agent-iq4_nl.gguf b/mem-agent-iq4_nl.gguf new file mode 100644 index 0000000..01d619e --- /dev/null +++ b/mem-agent-iq4_nl.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c8d331c3a74b4590af17bf45a3077f8ab556db55e4e9659b77d0131d9ac1808 +size 2281065600 diff --git a/mem-agent-iq4_xs.gguf b/mem-agent-iq4_xs.gguf new file mode 100644 index 0000000..2f6d571 --- /dev/null +++ b/mem-agent-iq4_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5042273018b9349e9ea678294370eeedba5d6050b0ff60567767df84e97a00cd +size 2270751360 diff --git a/mem-agent-q2_k_m.gguf b/mem-agent-q2_k_m.gguf new file mode 100644 index 0000000..b23915f --- /dev/null +++ b/mem-agent-q2_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:601f27e464bc73e902d0f9eff13d8e316845e777f1e047ae764f3218cb7f96ed +size 1542925440 diff --git a/mem-agent-q2_k_s.gguf b/mem-agent-q2_k_s.gguf new file mode 100644 index 0000000..540bc2e --- /dev/null +++ b/mem-agent-q2_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc3b1508bdfc5674a9418ac3b2a46fbbdf85d73533a2e29f7e1b833b1a25f443 +size 1491267200 diff --git a/mem-agent-q3_k_m.gguf b/mem-agent-q3_k_m.gguf new file mode 100644 index 0000000..3127222 --- /dev/null +++ b/mem-agent-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc534302b38eb2a8587ab1c6bfc461310ce86480092f9135456208425864f33b +size 2007903360 diff --git a/mem-agent-q3_k_s.gguf b/mem-agent-q3_k_s.gguf new file mode 100644 index 0000000..074f49d --- /dev/null +++ b/mem-agent-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9f846762f3c53a95376078e8d428669d6dc4c36093d4b69710d61459f80724 +size 1959283840 diff --git a/mem-agent-q4_0.gguf b/mem-agent-q4_0.gguf new file mode 100644 index 0000000..56470ed --- /dev/null +++ b/mem-agent-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321163d5e08142c888b9bb4faa9694a61093082b377c734802427f233df429ca +size 2269269120 diff --git a/mem-agent-q4_1.gguf b/mem-agent-q4_1.gguf new file mode 100644 index 0000000..5e94e6c --- /dev/null +++ b/mem-agent-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81461c71c1ae2809b57c47003683b93e3655002e4ae0094176cc841a6a4d193b +size 2520661120 diff --git a/mem-agent-q4_k_m.gguf b/mem-agent-q4_k_m.gguf new file mode 100644 index 0000000..c01c417 --- /dev/null +++ b/mem-agent-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3a683152b784a1b4f57ff90d32a3536c24e6fbba53beaa909600c13c1cff738 +size 2478520960 diff --git a/mem-agent-q4_k_s.gguf b/mem-agent-q4_k_s.gguf new file mode 100644 index 0000000..b2c7773 --- /dev/null +++ b/mem-agent-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:781bb021f7a452bb26bef247eb970af29c24f552c4983f42d83f0f2a841b350b +size 2355899520 diff --git a/mem-agent-q5_0.gguf b/mem-agent-q5_0.gguf new file mode 100644 index 0000000..7bd00d1 --- /dev/null +++ b/mem-agent-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c316611d34753c66adc342946e4bed869257dcf2f3000b7e2a4396b65e6525d +size 2772053120 diff --git a/mem-agent-q5_1.gguf b/mem-agent-q5_1.gguf new file mode 100644 index 0000000..59aaaea --- /dev/null +++ b/mem-agent-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a81e2d18c4078e29d4f46d7fc975fb5f1c1b9879525f579f66565218c74e93a2 +size 3023445120 diff --git a/mem-agent-q8_0.gguf b/mem-agent-q8_0.gguf new file mode 100644 index 0000000..604f843 --- /dev/null +++ b/mem-agent-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d9fc763bd96f3b600438edc9b1f8a142c449a82bead9237d2cc8d8b078934b +size 4280404800