commit 9d4ccbe976a23ae37b17dd6d86a5947003254c03 Author: ModelHub XC Date: Tue Jul 21 01:41:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ebc20e2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Gemma-2-9B-mix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.IQ4_XS.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.IQ4_XS.gguf new file mode 100644 index 0000000..56df375 --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d11fa8184e0960547318cb27cae14246dc5f9a716a31afa1a567d5aa920253df +size 4484364064 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q2_K.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q2_K.gguf new file mode 100644 index 0000000..ebf7165 --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7997d5cee1ebf3d50f4a0062f2936c84d04b278444b83c2a8fe784b923d9e47 +size 3179132704 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_L.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_L.gguf new file mode 100644 index 0000000..d8cae68 --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a1f8b5ed4303a3d3093ba40532307b6fe4d6356c1a36393d6fd96f5e99d008 +size 4321957664 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_M.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_M.gguf new file mode 100644 index 0000000..987edbc --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c1efbc9e577829136d3016308013941eca590bba15b7217731e66dd5390836 +size 4018919200 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_S.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_S.gguf new file mode 100644 index 0000000..771bd65 --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb0c5280064f823ce9e5edf61748c5bd84d4cfc0dc7ae0370acce4e0ced6f529 +size 3664500512 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_M.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_M.gguf new file mode 100644 index 0000000..1708e01 --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5112018aed0c6069ff8de5f3707f12e7e2bdb4c1c520aa5d0c9d21a7a475a196 +size 4920735520 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_S.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_S.gguf new file mode 100644 index 0000000..c76d141 --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df727a0d681dca799e7edeae53ec02767fb14804fc983181593f0ff70f3d77d5 +size 4692670240 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_M.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_M.gguf new file mode 100644 index 0000000..370cb79 --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:857c8078163c57b033b85d0b80410a614d8a8cc252c90a216dc6fa8dc0e315cc +size 5732988704 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_S.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_S.gguf new file mode 100644 index 0000000..34a98dc --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df74d4a00d60ff9ec2a1b33d466eac6dd525886206391422b529a86c92db4e8d +size 5599295264 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q6_K.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q6_K.gguf new file mode 100644 index 0000000..c2f49b6 --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7825c769378c20f6f97b409832f62592e5cb0ea6ce701a2d56cd86f5980009ff +size 6596007712 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.Q8_0.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.Q8_0.gguf new file mode 100644 index 0000000..30effef --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25e178eb61fe296c220f5fe2b4ae7212fcdcd8ebaba11634cbc470506d748291 +size 8540772128 diff --git a/Llama-3.1-8B-Gemma-2-9B-mix.f16.gguf b/Llama-3.1-8B-Gemma-2-9B-mix.f16.gguf new file mode 100644 index 0000000..488bf7c --- /dev/null +++ b/Llama-3.1-8B-Gemma-2-9B-mix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fd91a8ee8bce86055bcae626cf145a8afff09d5af9feba251d624724356c36e +size 16068892448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..79fe07c --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/Llama-3.1-8B-Gemma-2-9B-mix +language: +- en +library_name: transformers +model_name: Llama-3.1-8B-Gemma-2-9B-mix +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Llama-3.1-8B-Gemma-2-9B-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/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Gemma-2-9B-mix-GGUF/resolve/main/Llama-3.1-8B-Gemma-2-9B-mix.f16.gguf) | f16 | 16.2 | 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. + +