commit b92aac247b49f19a81df4a8587c44021c44a4295 Author: ModelHub XC Date: Sat Jun 27 03:16:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d1e6321 --- /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 +MT5-IGMAMU-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-IGMAMU-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT5-IGMAMU-gemma-2-9B.IQ4_XS.gguf b/MT5-IGMAMU-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..3a48c19 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edddfea6d3f617e0a29519400a9aff24391c98ccf4bc6cbbd164b7e85d21a32a +size 5223171904 diff --git a/MT5-IGMAMU-gemma-2-9B.Q2_K.gguf b/MT5-IGMAMU-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..9a1508c --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d0ed4fd70ef003f673846e232aa671e09f664741c0b7663c0a201149ab4b86 +size 3805398848 diff --git a/MT5-IGMAMU-gemma-2-9B.Q3_K_L.gguf b/MT5-IGMAMU-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..7c841f0 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1e697db9d377e2fb025b554659fa21e5eeef27c5e4e36a83e53fe7ab05d1ba2 +size 5132453696 diff --git a/MT5-IGMAMU-gemma-2-9B.Q3_K_M.gguf b/MT5-IGMAMU-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..f99d27f --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d19a2f6f76f32c6dc0415fdfad763bb1db1f8d0ab8e4bd9da0069094ed6db0 +size 4761782080 diff --git a/MT5-IGMAMU-gemma-2-9B.Q3_K_S.gguf b/MT5-IGMAMU-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..aacee51 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ee81d6e7efd9ed801b227007d4f3c113bd627cf7bc88cd439ce38779b04f8c +size 4337665856 diff --git a/MT5-IGMAMU-gemma-2-9B.Q4_K_M.gguf b/MT5-IGMAMU-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..3e42759 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da327bbf293bd3f628863af254b7d9743d4847605f141ab406c2a9bc2cb6867 +size 5761058624 diff --git a/MT5-IGMAMU-gemma-2-9B.Q4_K_S.gguf b/MT5-IGMAMU-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..7102a75 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:550faa33633bc850c3ed817f2a90505ffdb6c38b2c5a63c7434cc024eb9b6308 +size 5478926144 diff --git a/MT5-IGMAMU-gemma-2-9B.Q5_K_M.gguf b/MT5-IGMAMU-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..2d32447 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1b14b80965c304daf38bed0cf35060eadf3d39bb58a8280da327cbd7418c18 +size 6647367488 diff --git a/MT5-IGMAMU-gemma-2-9B.Q5_K_S.gguf b/MT5-IGMAMU-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..50b0ad5 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41d3d878e65373aa088c59be0fbb252028ecd78cfec7ca247fbfcc650b753e35 +size 6483593024 diff --git a/MT5-IGMAMU-gemma-2-9B.Q6_K.gguf b/MT5-IGMAMU-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..208a340 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed86a3c44dc590c49345d729fb46caf497f653d17624f8cb81cbdea70e8fdd42 +size 7589070656 diff --git a/MT5-IGMAMU-gemma-2-9B.Q8_0.gguf b/MT5-IGMAMU-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..f3f3f04 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:101d0ff41ec293b442b019bd958aab42f2cffa8b2532cc7939d26980d83108ec +size 9827149632 diff --git a/MT5-IGMAMU-gemma-2-9B.f16.gguf b/MT5-IGMAMU-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..4f63e31 --- /dev/null +++ b/MT5-IGMAMU-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a1fbd1c6169ee3ed062747794f0f56ee958e8ed934361c6f20724f8a4bb5798 +size 18490681152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ea1128e --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT5-IGMAMU-gemma-2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT5-IGMAMU-gemma-2-9B + + +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/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-IGMAMU-gemma-2-9B-GGUF/resolve/main/MT5-IGMAMU-gemma-2-9B.f16.gguf) | f16 | 18.6 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +