commit d8f21a24fc21d37c07dfe58a44b69fed165dc8ba Author: ModelHub XC Date: Mon Jun 29 08:09:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..498af7f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,45 @@ +*.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 +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Genius_Magpie-25K_LLaMA3.1-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.IQ4_XS.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..df587db --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3582d6356ba135a359064666b817f39922d9f4140f88c641600aa62e692b5587 +size 4484367872 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q2_K.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..6e965f9 --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2aec05c1bcbcba71c2187029f998f3a27fa366012489d5a7019928d8619e25 +size 3179136512 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_L.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..0b56bab --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04d20821f9cd4527d23f7188472138328212898a3dbcf9ff7527c39ffced36e +size 4321961472 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_M.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..7ab213e --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eee1dc7975b53f38ef43d7a2bb4abd5a1e1a3bbf7325c2945195d87f138ab03 +size 4018923008 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_S.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..c498779 --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8412f1d02fbd89089f0e0c8ab21245dc9cd76fd04d49c32b7cab6c6b2c5eb7a +size 3664504320 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_M.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..c7bc8f7 --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af9dbb69c1345139ffeb4571df85ff72aa6224d7e9d88d85c2d4f5e7a812559c +size 4920739328 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_S.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..60b364d --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e914130d279b650c954e5d2e4e3aa188518d055331c171400c694f780bf0e2 +size 4692674048 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_M.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..1144f70 --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4df40e9f51c1a7a6c0905f971eba8aa6185bd48631b9a322fb868730d52bd3db +size 5732992512 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_S.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..29ff476 --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e76bb8239e7dcfc415a26ce09585b84b401246dfcb301be38d92f20888039673 +size 5599299072 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q6_K.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..e650958 --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260249213b9a31d1169168871f1f7a252350737371434e2eeade422e2b8c6150 +size 6596011520 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q8_0.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..6c87b9e --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f01f51bc1fd275f6b5ad5cf3c26d23bb0a49bd08c941a65a4c662611b71562d1 +size 8540775936 diff --git a/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.f16.gguf b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.f16.gguf new file mode 100644 index 0000000..cb6000d --- /dev/null +++ b/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2617a01d939c9b1e98f9b5fa2a2b47e2a0d8555c60d74b6f3f094ac6d995225e +size 16068896256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..05fe627 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: xufangzhi/Genius_Magpie-25K_LLaMA3.1-8B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/xufangzhi/Genius_Magpie-25K_LLaMA3.1-8B-Instruct + + +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/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Genius_Magpie-25K_LLaMA3.1-8B-Instruct-GGUF/resolve/main/Genius_Magpie-25K_LLaMA3.1-8B-Instruct.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. + +