commit 1cbb1c9a2f2cf6c4ac376fb7bb37cf3bd09589f3 Author: ModelHub XC Date: Wed Oct 21 22:50:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/mem-agent-f32-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1343398 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,61 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm 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.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent.F32.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent.Q5_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.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent.BF16.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent.F16.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mem-agent.Q3_K_L.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.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..6803604 --- /dev/null +++ b/README.md @@ -0,0 +1,43 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- driaforall/mem-agent +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +- agent +--- + +# **mem-agent-f32-gguf** + +> [driaforall/mem-agent](https://huggingface.co/driaforall/mem-agent) is an agentic model based on Qwen3-4B-Thinking-2507, fine-tuned using GSPO (Zheng et al., 2025) to interact with an Obsidian-inspired, markdown-based memory system for advanced retrieval, updating, and clarification tasks. It is structured around agentic scaffolding that leverages dedicated tags and tool APIs for file and directory operations, supporting memory filtering and obfuscation, and evaluated on the md-memory-bench where it outperformed most open and closed models except qwen/qwen3-235b-a22b-thinking-2507, with an overall benchmark score of 0.75. The model is designed for use as an MCP server or standalone, and relies on linked markdown files to manage user and entity data, enabling seamless, flexible document-like memory manipulation for agentic or personal assistant scenarios. + +## Model Files + +| File Name | Quant Type | File Size | +| - | - | - | +| mem-agent.BF16.gguf | BF16 | 8.05 GB | +| mem-agent.F16.gguf | F16 | 8.05 GB | +| mem-agent.F32.gguf | F32 | 16.1 GB | +| mem-agent.Q2_K.gguf | Q2_K | 1.67 GB | +| mem-agent.Q3_K_L.gguf | Q3_K_L | 2.24 GB | +| mem-agent.Q3_K_M.gguf | Q3_K_M | 2.08 GB | +| mem-agent.Q3_K_S.gguf | Q3_K_S | 1.89 GB | +| mem-agent.Q4_K_M.gguf | Q4_K_M | 2.5 GB | +| mem-agent.Q4_K_S.gguf | Q4_K_S | 2.38 GB | +| mem-agent.Q5_K_M.gguf | Q5_K_M | 2.89 GB | +| mem-agent.Q5_K_S.gguf | Q5_K_S | 2.82 GB | +| mem-agent.Q6_K.gguf | Q6_K | 3.31 GB | +| mem-agent.Q8_0.gguf | Q8_0 | 4.28 GB | + +## Quants Usage + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..5d0c447 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "qwen3" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/mem-agent.BF16.gguf b/mem-agent.BF16.gguf new file mode 100644 index 0000000..16a4062 --- /dev/null +++ b/mem-agent.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bf5b5c9d1a7029dd3f8ef274e7319562df4e4a096560dc1fa82bca60d4223da +size 8051284768 diff --git a/mem-agent.F16.gguf b/mem-agent.F16.gguf new file mode 100644 index 0000000..582fb8b --- /dev/null +++ b/mem-agent.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c06d836a51d99dbbf59ad7a3c6b30cb4802cda79e5da86313b1c3bbe086f7c +size 8051284768 diff --git a/mem-agent.F32.gguf b/mem-agent.F32.gguf new file mode 100644 index 0000000..fbbf2ee --- /dev/null +++ b/mem-agent.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ffda3add3fd962d512b651f670e5bd0e91600f99f09ebec6c35db813b6bf221 +size 16095828768 diff --git a/mem-agent.Q2_K.gguf b/mem-agent.Q2_K.gguf new file mode 100644 index 0000000..9c642e9 --- /dev/null +++ b/mem-agent.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6998c19cd50fc7c20570ffdb882d62cc43a024edf6a4f5cbd39b0f6519b3526d +size 1669499168 diff --git a/mem-agent.Q3_K_L.gguf b/mem-agent.Q3_K_L.gguf new file mode 100644 index 0000000..0dd546c --- /dev/null +++ b/mem-agent.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7bc791f9161a04e12d1b22ef21dce01838fa312df73ff127dd5e8bf54ac490a +size 2239785248 diff --git a/mem-agent.Q3_K_M.gguf b/mem-agent.Q3_K_M.gguf new file mode 100644 index 0000000..cae7eb3 --- /dev/null +++ b/mem-agent.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4386c77407b0a9851b4e1d978918f6612fedab47d69a4773b00e81492d6a034d +size 2075617568 diff --git a/mem-agent.Q3_K_S.gguf b/mem-agent.Q3_K_S.gguf new file mode 100644 index 0000000..755c969 --- /dev/null +++ b/mem-agent.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38a3e8986c91bfa567f9d5fbd6b05a6d92202b3e2d056b7f3eda14e90c69ed2 +size 1886996768 diff --git a/mem-agent.Q4_K_M.gguf b/mem-agent.Q4_K_M.gguf new file mode 100644 index 0000000..ae4a22e --- /dev/null +++ b/mem-agent.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944ce327e8daac14a0551943bc46739dc511d032ff9ccd2218941326d431e77e +size 2497280288 diff --git a/mem-agent.Q4_K_S.gguf b/mem-agent.Q4_K_S.gguf new file mode 100644 index 0000000..5024fe2 --- /dev/null +++ b/mem-agent.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71be3233caa95c56c61a4fb0dd78d47102990057399f93152048cd8b6f51cf9e +size 2383309088 diff --git a/mem-agent.Q5_K_M.gguf b/mem-agent.Q5_K_M.gguf new file mode 100644 index 0000000..65ce287 --- /dev/null +++ b/mem-agent.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c510a04b7b3cae88265bcabda3c3be4ca026b147b95420ffbb0db97d1f155bd1 +size 2889513248 diff --git a/mem-agent.Q5_K_S.gguf b/mem-agent.Q5_K_S.gguf new file mode 100644 index 0000000..1249e75 --- /dev/null +++ b/mem-agent.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3dc79963310763a73cd96851ae685ea584204bd374142b1243adf522b2225be +size 2823711008 diff --git a/mem-agent.Q6_K.gguf b/mem-agent.Q6_K.gguf new file mode 100644 index 0000000..7b0e180 --- /dev/null +++ b/mem-agent.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453dfc223f641b466f09b27f5298ba28b4ed5f5e931664fcbed4b7f1c18f67f8 +size 3306260768 diff --git a/mem-agent.Q8_0.gguf b/mem-agent.Q8_0.gguf new file mode 100644 index 0000000..88b6ec9 --- /dev/null +++ b/mem-agent.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef2322b04c7d8753e52f7e814b0059cb6f7141adc5f2991ec7280d8662306e7 +size 4280404768