commit e17e648711f0569c2a85976392681d144f159c31 Author: ModelHub XC Date: Wed Jun 24 16:31:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/orca_mini_v5_8b_dpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6ca0eb4 --- /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 +orca_mini_v5_8b_dpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.f16.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +orca_mini_v5_8b_dpo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..532ea84 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: pankajmathur/orca_mini_v5_8b_dpo +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/pankajmathur/orca_mini_v5_8b_dpo + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-i1-GGUF +## 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/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/orca_mini_v5_8b_dpo-GGUF/resolve/main/orca_mini_v5_8b_dpo.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. + + diff --git a/orca_mini_v5_8b_dpo.IQ4_XS.gguf b/orca_mini_v5_8b_dpo.IQ4_XS.gguf new file mode 100644 index 0000000..a2fb695 --- /dev/null +++ b/orca_mini_v5_8b_dpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab8294de690b673f3f023d7be08cb9a6fff700e8b2b03805164d1dd1169bcfc +size 4484374336 diff --git a/orca_mini_v5_8b_dpo.Q2_K.gguf b/orca_mini_v5_8b_dpo.Q2_K.gguf new file mode 100644 index 0000000..3582a9a --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdcbe71d659dbff549cd4158e94b42d6bc005bfde616c87e52b17f491b51f907 +size 3179141312 diff --git a/orca_mini_v5_8b_dpo.Q3_K_L.gguf b/orca_mini_v5_8b_dpo.Q3_K_L.gguf new file mode 100644 index 0000000..cc90936 --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7224d987c5bbcba2f97970024c41e065aec61a4e6932485e3a45a70928eedd +size 4321967104 diff --git a/orca_mini_v5_8b_dpo.Q3_K_M.gguf b/orca_mini_v5_8b_dpo.Q3_K_M.gguf new file mode 100644 index 0000000..b80f86d --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:404e4aa7f42535cbd75e7ce1b69782c5c576b21d3dd602056aed79cd1198ee91 +size 4018928640 diff --git a/orca_mini_v5_8b_dpo.Q3_K_S.gguf b/orca_mini_v5_8b_dpo.Q3_K_S.gguf new file mode 100644 index 0000000..5b92a7e --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d61207824214c842f7725348bd5ed4a343a465fe5b1a1e9e5b00dda4e1b35843 +size 3664509952 diff --git a/orca_mini_v5_8b_dpo.Q4_K_M.gguf b/orca_mini_v5_8b_dpo.Q4_K_M.gguf new file mode 100644 index 0000000..a78880c --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b8a2a346b73ff38c56c41caa76a075319a5a3d928e84965599188670567ccc +size 4920746048 diff --git a/orca_mini_v5_8b_dpo.Q4_K_S.gguf b/orca_mini_v5_8b_dpo.Q4_K_S.gguf new file mode 100644 index 0000000..d49531a --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1334f48664bad00ded9759aa40f52b8e18c26ad98c55a17a90d5d0b063fbcd14 +size 4692680768 diff --git a/orca_mini_v5_8b_dpo.Q5_K_M.gguf b/orca_mini_v5_8b_dpo.Q5_K_M.gguf new file mode 100644 index 0000000..a00d29f --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ddf19329c07c0902f1ff29330e416aea6218f7b56ddf89ef27c6b9306dbc6f +size 5733000256 diff --git a/orca_mini_v5_8b_dpo.Q5_K_S.gguf b/orca_mini_v5_8b_dpo.Q5_K_S.gguf new file mode 100644 index 0000000..2e41550 --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4d5d50612d49b727d0293cedce3368f34fc90f17cec132442266916cf52590c +size 5599306816 diff --git a/orca_mini_v5_8b_dpo.Q6_K.gguf b/orca_mini_v5_8b_dpo.Q6_K.gguf new file mode 100644 index 0000000..beedaab --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b415d07a62ff50c77f1e28ebfcbc08796296543423940a573b314be56cedc5f8 +size 6596020352 diff --git a/orca_mini_v5_8b_dpo.Q8_0.gguf b/orca_mini_v5_8b_dpo.Q8_0.gguf new file mode 100644 index 0000000..ea6ef78 --- /dev/null +++ b/orca_mini_v5_8b_dpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e8ab334088c64882fce0838483ece852f440b757d16efcc79f5c8769760197c +size 8540788736 diff --git a/orca_mini_v5_8b_dpo.f16.gguf b/orca_mini_v5_8b_dpo.f16.gguf new file mode 100644 index 0000000..ec5ae3b --- /dev/null +++ b/orca_mini_v5_8b_dpo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9633d3d66084c541f953f3166bb1ab72d6c5bff814c3e651a59178471e821eb +size 16068924416