commit 7c812b32b6048ceffab798f6e61f27f147b72bb3 Author: ModelHub XC Date: Tue Sep 29 23:27:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9b44902 --- /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 +Gemma-2-9B-Llama-2-7b-mix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-2-9B-Llama-2-7b-mix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma-2-9B-Llama-2-7b-mix.IQ4_XS.gguf b/Gemma-2-9B-Llama-2-7b-mix.IQ4_XS.gguf new file mode 100644 index 0000000..3c7e7ea --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d42fbfcecb59c21fba127e1189433673afab264ce8d0ed04ca6fdcd361968aa4 +size 5223171680 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q2_K.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q2_K.gguf new file mode 100644 index 0000000..4f258d7 --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:776f941b36c751995443c5767ca83a66805bcb5449bdf926d9f086e83417c94e +size 3805398624 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q3_K_L.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q3_K_L.gguf new file mode 100644 index 0000000..d2fb905 --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5220c89092e337e1d486401382feb1b6e19acfa0772143274707dd99477b48a1 +size 5132453472 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q3_K_M.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q3_K_M.gguf new file mode 100644 index 0000000..8764c7a --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49583bc21060b18e5c909fe74d5ce45660f7615261af588555b3645a9d18aff4 +size 4761781856 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q3_K_S.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q3_K_S.gguf new file mode 100644 index 0000000..e30144c --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69061d14f72e557eee0fd38a87dd010c04f4454161dc74c3837bba367386de65 +size 4337665632 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q4_K_M.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q4_K_M.gguf new file mode 100644 index 0000000..f1f37d8 --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f6f79a3b9136d6a943ef6e7e3d5672300ec654dbedca2cec8957eab15b4a38 +size 5761058400 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q4_K_S.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q4_K_S.gguf new file mode 100644 index 0000000..332533c --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcc650f1fb94e9e987c071e8c29b36f4220fa9ff933c5f6028ac29babb08b7f0 +size 5478925920 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q5_K_M.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q5_K_M.gguf new file mode 100644 index 0000000..8683b06 --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d2d80eecdc58bca9f089ac6699537659c1ae8bfb3495e6521d2d4367cb2689 +size 6647367264 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q5_K_S.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q5_K_S.gguf new file mode 100644 index 0000000..a8e5833 --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d78ad6c3ba9189ff5f7e6063a45b06f68506a97f3c29a97b13d677e00fcfe591 +size 6483592800 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q6_K.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q6_K.gguf new file mode 100644 index 0000000..00c19b9 --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befe0cd7a8a7bcc150d14e3b56b83624682b7fbcc2ed3fcf227740dbe22468cf +size 7589070432 diff --git a/Gemma-2-9B-Llama-2-7b-mix.Q8_0.gguf b/Gemma-2-9B-Llama-2-7b-mix.Q8_0.gguf new file mode 100644 index 0000000..3c345f0 --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9399e103421bdafa7f7eeb77f4a6844e20ebc9a04c8705cc18196571aeb7f610 +size 9827149408 diff --git a/Gemma-2-9B-Llama-2-7b-mix.f16.gguf b/Gemma-2-9B-Llama-2-7b-mix.f16.gguf new file mode 100644 index 0000000..98204ef --- /dev/null +++ b/Gemma-2-9B-Llama-2-7b-mix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:166306517aa246db724d4cd862e9cdec4f4e30b3eb7d5acf06c4ac5582f063c9 +size 18490680928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aa7065b --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/Gemma-2-9B-Llama-2-7b-mix +language: +- en +library_name: transformers +model_name: Gemma-2-9B-Llama-2-7b-mix +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Gemma-2-9B-Llama-2-7b-mix + + +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/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-2-9B-Llama-2-7b-mix-GGUF/resolve/main/Gemma-2-9B-Llama-2-7b-mix.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. + +