commit 9225f9f95f5c7a9d842acffb0273b3ddcb1f0ede Author: ModelHub XC Date: Tue Jun 2 19:56:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MemSifter-4B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..17cb62a --- /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 +MemSifter-4B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MemSifter-4B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MemSifter-4B-Thinking.IQ4_XS.gguf b/MemSifter-4B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..e6e2403 --- /dev/null +++ b/MemSifter-4B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83226540f37814e28d5c39bb1cbc39ff35193def5f6f47b2e5055bbaf9dee758 +size 2492949664 diff --git a/MemSifter-4B-Thinking.Q2_K.gguf b/MemSifter-4B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..314c805 --- /dev/null +++ b/MemSifter-4B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0015c19e4fc61a62299574da16f0e6385a2b6889e995581e81a07f5154c80c +size 1797126304 diff --git a/MemSifter-4B-Thinking.Q3_K_L.gguf b/MemSifter-4B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..fe81963 --- /dev/null +++ b/MemSifter-4B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c7259ec03632e98141c7d1713770e926de49b8e0e1f6281cf73f3f5b5e09af +size 2406915744 diff --git a/MemSifter-4B-Thinking.Q3_K_M.gguf b/MemSifter-4B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..d8f19ea --- /dev/null +++ b/MemSifter-4B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c503abefacb61a1b4f3938c54f27dbaf5522777e20577374d095d0d5787b654 +size 2242748064 diff --git a/MemSifter-4B-Thinking.Q3_K_S.gguf b/MemSifter-4B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..14a3042 --- /dev/null +++ b/MemSifter-4B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc15930ac181912de9426bc2a28ac7d9cc8d0ca87f3a7d38bf5f3b0318f1803b +size 2054127264 diff --git a/MemSifter-4B-Thinking.Q4_K_M.gguf b/MemSifter-4B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..6b44fa7 --- /dev/null +++ b/MemSifter-4B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71dceb86369efd2e62932a1b5e0eefdd821babf0fc464bd56e830c1b5620da7c +size 2716069024 diff --git a/MemSifter-4B-Thinking.Q4_K_S.gguf b/MemSifter-4B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..535459b --- /dev/null +++ b/MemSifter-4B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d83c0f86453f152d7048872cbfa0a3a607ac48ce05a14a1bb9bbf0c9e1409d92 +size 2602097824 diff --git a/MemSifter-4B-Thinking.Q5_K_M.gguf b/MemSifter-4B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..f6638cf --- /dev/null +++ b/MemSifter-4B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88c1fee401dd9dc5f1014744c41742ddae1c36507fdbaba754da703ad39506d +size 3156921504 diff --git a/MemSifter-4B-Thinking.Q5_K_S.gguf b/MemSifter-4B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..fe7c833 --- /dev/null +++ b/MemSifter-4B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcf054445b0b2dcff1bba62f59129f128feb0eacdc55acb427bf2262b2fc8ec6 +size 3091119264 diff --git a/MemSifter-4B-Thinking.Q6_K.gguf b/MemSifter-4B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..8d265f4 --- /dev/null +++ b/MemSifter-4B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:972c5f438bada92984d9393569437e269ae1e13fe2d44ae3cca21a47d017bde1 +size 3625327264 diff --git a/MemSifter-4B-Thinking.Q8_0.gguf b/MemSifter-4B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..55f4a59 --- /dev/null +++ b/MemSifter-4B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ff78d48d9f5002381a752d0930e40cb4f762220ef0a1288a5dd190746c8989 +size 4693671584 diff --git a/MemSifter-4B-Thinking.f16.gguf b/MemSifter-4B-Thinking.f16.gguf new file mode 100644 index 0000000..f71fb6b --- /dev/null +++ b/MemSifter-4B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ad302fd0086eb4863ebfcbb4064e5687b3ffbf596d47ea92e9584b45a52dd46 +size 8829197984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..036fe34 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: zstanjj/MemSifter-4B-Thinking +language: +- en +- zh +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zstanjj/MemSifter-4B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MemSifter-4B-Thinking-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-4B-Thinking.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MemSifter-4B-Thinking-GGUF/resolve/main/MemSifter-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. + +