commit e866e55714d9c2993819dcf08f262ccf6149bf55 Author: ModelHub XC Date: Wed Jul 1 19:55:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed21baa --- /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 +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.IQ4_XS.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..7ca17a2 --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3641b0f8235e92494d77e301636bdcb56dc2e212ebf81a72843402edd54c89e5 +size 5223171936 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q2_K.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q2_K.gguf new file mode 100644 index 0000000..a6a2912 --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:214690a9975d30ab8f2c76e56b9a8cc4116797982da720f0845a574a1ea0891c +size 3805398880 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_L.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..02a012d --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51569a0a6a6c71fc2f678ed38446a054a4e4048fd6d90afca73f714f26f02028 +size 5132453728 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_M.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..e1f5093 --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:972f22826a9620b2391aa193212bf454f721c450620c35441da077a2d94b7ff3 +size 4761782112 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_S.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..4e068a4 --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90e2145fe7c2cd5209fc3a0e9d0c161b614d287a16cf457fcd55c6444fbbd313 +size 4337665888 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_M.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..268b2ac --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1b45b92862c262ea48856d3ef251a6367af77155394aa5881081e45b667879 +size 5761058656 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_S.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..e90000a --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091f31a1af4a641307c4166dfedfc14c9c90f8e93f42159b713dcb1382e2c4f3 +size 5478926176 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_M.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..7b6fe76 --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d93036169c6c0500a560b0db6ce1c2063b75331343e261bbd30d5da9d21595 +size 6647367520 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_S.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..40a3488 --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dec591a160315ea733e42cf06c229f0bea6f684ef87eb128a3eda264ce12466 +size 6483593056 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q6_K.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q6_K.gguf new file mode 100644 index 0000000..c83411c --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b162d5e11df39fe085190b2f3cad42f075ec570d4a61e9cdc195e41a83f14802 +size 7589070688 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q8_0.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q8_0.gguf new file mode 100644 index 0000000..5054c19 --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c7481a1599f554e14e5fbf8f142b54586c712f13fb3e6743800cc182ddd80a2 +size 9827149664 diff --git a/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.f16.gguf b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.f16.gguf new file mode 100644 index 0000000..0f99695 --- /dev/null +++ b/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5406ba5fee4d21595e09815e488fd31953ec13d0d9c1ab1f90c1b96deb6a62 +size 18490681184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2d213e9 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B + + +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/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B-GGUF/resolve/main/MT3-Gen4-GP-gemma-2-MT5g3MT2g2-9B.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. + +