commit 98cc60b2067e82aa079666215c7c99f21f673eca Author: ModelHub XC Date: Tue Sep 8 11:44:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..35a081f --- /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 +MemSFT-Qwen3-Bio-Memory-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MemSFT-Qwen3-Bio-Memory-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MemSFT-Qwen3-Bio-Memory-4B.IQ4_XS.gguf b/MemSFT-Qwen3-Bio-Memory-4B.IQ4_XS.gguf new file mode 100644 index 0000000..259903f --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c853ee9de116603f878c127f3af935a34fc84d748efa84a8a978375355d1acce +size 2492019936 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q2_K.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q2_K.gguf new file mode 100644 index 0000000..c7c9881 --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8252b1a265d6aadd01e35c8ed8d6b2819a6772f818ae198b3d1822f6ac68a078 +size 1796335424 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_L.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_L.gguf new file mode 100644 index 0000000..c2c4d62 --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25471171368e185f083f147092fcef025bda1eec9cc163e34a8adf6199347a17 +size 2406055424 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_M.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_M.gguf new file mode 100644 index 0000000..b4ba4eb --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a1ed3135ba1af06b703a08bdac47c3d0b5f7dfb76602be0acdbc5f7d0826f1 +size 2241887744 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_S.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_S.gguf new file mode 100644 index 0000000..fcdb043 --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef06bc68077975f013dbb5e0f885851a0510e2726787f9d66845d5225bca187 +size 2053266944 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q4_K_M.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q4_K_M.gguf new file mode 100644 index 0000000..546ea97 --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab259ffd55a2b6823416158e9b532ff679976de90ce8771ac6f574626eca569 +size 2715117920 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q4_K_S.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q4_K_S.gguf new file mode 100644 index 0000000..685cd74 --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66d02d07a68526a91ad2890224d87e4a7237be821e2f006a480940bca503464f +size 2601146720 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q5_K_M.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q5_K_M.gguf new file mode 100644 index 0000000..942b9d2 --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6edca22a7e71cdf32907936eb7b8a633529bd16e4720a90a2adf14703ef5bd86 +size 3155884960 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q5_K_S.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q5_K_S.gguf new file mode 100644 index 0000000..fdb7289 --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae26b9d20300c2dba9160fffb0bd24f517612839d31ecd977a1b8b1c6cefacb8 +size 3090082720 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q6_K.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q6_K.gguf new file mode 100644 index 0000000..9b64353 --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec272f91b4f245eda31cb703368c670116236413a40a9a4a77ebbff6374a48ef +size 3624199968 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.Q8_0.gguf b/MemSFT-Qwen3-Bio-Memory-4B.Q8_0.gguf new file mode 100644 index 0000000..4ad7f4e --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a5f676a5354b06a8cd0dcd0d0da1aaaf98684993e0a5f8e86fee211dc0d7361 +size 4692213152 diff --git a/MemSFT-Qwen3-Bio-Memory-4B.f16.gguf b/MemSFT-Qwen3-Bio-Memory-4B.f16.gguf new file mode 100644 index 0000000..2a25268 --- /dev/null +++ b/MemSFT-Qwen3-Bio-Memory-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08618c7135d4a53e5fd60f4375d1e08147452449cfaa962b53e5c56c3ab054fc +size 8826457952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bbd87cd --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Jiarui-Wang/MemSFT-Qwen3-Bio-Memory-4B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- memsft +- memory-decoder +- biology +- biology-instructions +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jiarui-Wang/MemSFT-Qwen3-Bio-Memory-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MemSFT-Qwen3-Bio-Memory-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-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/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MemSFT-Qwen3-Bio-Memory-4B-GGUF/resolve/main/MemSFT-Qwen3-Bio-Memory-4B.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. + +