commit 840598fb2b6384139794fc09fffbb8a3d97b5d91 Author: ModelHub XC Date: Fri May 1 09:23:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MemReader-4B-thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..98b5f56 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +MemReader-4B-thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MemReader-4B-thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MemReader-4B-thinking.IQ4_XS.gguf b/MemReader-4B-thinking.IQ4_XS.gguf new file mode 100644 index 0000000..59922be --- /dev/null +++ b/MemReader-4B-thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0e81217a9f9c462921c9f6d854d55ca2c07d42f9c1edb587dab7ce72a7c7379 +size 2492949888 diff --git a/MemReader-4B-thinking.Q2_K.gguf b/MemReader-4B-thinking.Q2_K.gguf new file mode 100644 index 0000000..3272b94 --- /dev/null +++ b/MemReader-4B-thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111c5ca26c3248a62e3a5567108d87e9fa493993f8e3fa3847fa97c83e88b253 +size 1797126528 diff --git a/MemReader-4B-thinking.Q3_K_L.gguf b/MemReader-4B-thinking.Q3_K_L.gguf new file mode 100644 index 0000000..a1fd759 --- /dev/null +++ b/MemReader-4B-thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43abd6d4063c8576429e7db94d5a06c0e8cb5cd566a4be61f6ed4db9dfba773a +size 2406915968 diff --git a/MemReader-4B-thinking.Q3_K_M.gguf b/MemReader-4B-thinking.Q3_K_M.gguf new file mode 100644 index 0000000..ab0f810 --- /dev/null +++ b/MemReader-4B-thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0065a62c92c7e7c123e65d82205f3460cb9dd0d8fc9aeb2fc33fc25fdc75b806 +size 2242748288 diff --git a/MemReader-4B-thinking.Q3_K_S.gguf b/MemReader-4B-thinking.Q3_K_S.gguf new file mode 100644 index 0000000..141eb94 --- /dev/null +++ b/MemReader-4B-thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21cf5b03b038f98e1c3455470ed981ba4e470ecb5df6d176da3fb23cb885f9f2 +size 2054127488 diff --git a/MemReader-4B-thinking.Q4_K_M.gguf b/MemReader-4B-thinking.Q4_K_M.gguf new file mode 100644 index 0000000..5f47167 --- /dev/null +++ b/MemReader-4B-thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9adba942b35d1254c1f328c6e29eb51fe4370b6cc65b806b4e8097a7d71ffd3f +size 2716069248 diff --git a/MemReader-4B-thinking.Q4_K_S.gguf b/MemReader-4B-thinking.Q4_K_S.gguf new file mode 100644 index 0000000..626ac56 --- /dev/null +++ b/MemReader-4B-thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960d6a80100112760da2d01299f8ad06cfda6fd2336f62daf7fababffb74a978 +size 2602098048 diff --git a/MemReader-4B-thinking.Q5_K_M.gguf b/MemReader-4B-thinking.Q5_K_M.gguf new file mode 100644 index 0000000..b516e60 --- /dev/null +++ b/MemReader-4B-thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b22e5ede11253dd2abdf5dc1fa7d9de7090c4aca28873197e091667d3d595369 +size 3156921728 diff --git a/MemReader-4B-thinking.Q5_K_S.gguf b/MemReader-4B-thinking.Q5_K_S.gguf new file mode 100644 index 0000000..e492605 --- /dev/null +++ b/MemReader-4B-thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b97482072837101c193651a17306e148fae1133bc18fa7f960de4ebcd75778 +size 3091119488 diff --git a/MemReader-4B-thinking.Q6_K.gguf b/MemReader-4B-thinking.Q6_K.gguf new file mode 100644 index 0000000..5c21c81 --- /dev/null +++ b/MemReader-4B-thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc1085d7a3fa56a7dfcaf5bd141685884d4d5ae5640b83887fe28cea3d678b8 +size 3625327488 diff --git a/MemReader-4B-thinking.Q8_0.gguf b/MemReader-4B-thinking.Q8_0.gguf new file mode 100644 index 0000000..039b6d1 --- /dev/null +++ b/MemReader-4B-thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f60a18da7fa9b18a9d2398cb27df10d0ba840abc85080172adf37004eabb3c0 +size 4693671808 diff --git a/MemReader-4B-thinking.f16.gguf b/MemReader-4B-thinking.f16.gguf new file mode 100644 index 0000000..30696c4 --- /dev/null +++ b/MemReader-4B-thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b54a056126a8c1cb47615b03c5e764cc447f241f0c9e3bebd33495a40b97fbe +size 8829198208 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5f674c3 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: IAAR-Shanghai/MemReader-4B-thinking +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen3 +- memory +- memory-extraction +- tool-calling +- reasoning +- agent +--- +## About + + + + + + + + + +static quants of https://huggingface.co/IAAR-Shanghai/MemReader-4B-thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MemReader-4B-thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MemReader-4B-thinking-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MemReader-4B-thinking-GGUF/resolve/main/MemReader-4B-thinking.f16.gguf) | f16 | 8.9 | 16 bpw, overkill | + +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) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +