commit d5f71d33f329af4d73f3566ecd720cc34e5ca7e3 Author: ModelHub XC Date: Thu Sep 3 21:04:40 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..997cbd6 --- /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 +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.IQ4_XS.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..4e6e39d --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c73f239faf8a821d9b6cad6629fc703c444c5baa4409c5ae6408f5f49c3192 +size 5223171936 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q2_K.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q2_K.gguf new file mode 100644 index 0000000..8bb5408 --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd83985850b52ab4a4a3b8c30dad80a959f9bf3648b6a2e72b59d8f4ed696aaf +size 3805398880 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_L.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..8e2205a --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f10ea146e61c8867de5bbd99eaa944ece1cb4f3996ec34844f80749366580dc +size 5132453728 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_M.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..59d7273 --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70c5e377276281f7475b6445025a155126c2a6ab4eaad977c57792600f584c69 +size 4761782112 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_S.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..4038237 --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbd50789ace3be050c5bb5c6d90af739b0d326cc4d19a866005573bdabce55a4 +size 4337665888 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_M.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..0ebddf3 --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba5d8d3f0b32bcbcbcd5cb0dc15eeefb09a215c8c0be8e030598f7347d05eed +size 5761058656 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_S.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..2eeafe3 --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a3b55983b089cf6847210c5a90e94065b94f9804f0b884832b471955774cea +size 5478926176 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_M.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..27e15ad --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306ebd18c13619cd1fc5b5735f05d0709d28bd9603e09d4a92fe8df7bb7e2af5 +size 6647367520 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_S.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..e4bff77 --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cb4ec76673e5780f760939a6f3bb29bcf6a38bfbe0eb15d4ae257501ec27e5 +size 6483593056 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q6_K.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q6_K.gguf new file mode 100644 index 0000000..15f74e7 --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6a7a562e057c308fb1b4855a884632a54d187eaebb8928ba3d6e5fed22c4358 +size 7589070688 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q8_0.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q8_0.gguf new file mode 100644 index 0000000..3a20ad4 --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d6702f490f45b1dac321d3eedfe59878f79532d87dcf7482c2ab9686ef08ab +size 9827149664 diff --git a/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.f16.gguf b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.f16.gguf new file mode 100644 index 0000000..abb568f --- /dev/null +++ b/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8e08488758c2decf638698b4353d9194132d8b9ec1cf8799946c4e0faea56fb +size 18490681184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..168c63c --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B + + +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/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B-GGUF/resolve/main/MT-Gen5-IF-gemma-2-MT5g4MT4g2-9B.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. + +