commit a5190f19d97b6036a0e5f1d2a5bd437e4bda78ab Author: ModelHub XC Date: Sun Jun 14 23:09:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..aa94ead --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-3-8B-Magpie-Pro-MT-UltraDPO2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_M.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_M.gguf new file mode 100644 index 0000000..db5a64f --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7705efc0de20190c0213a9badcff387512a8db8ee7371e865f1b9206aec07665 +size 3784823616 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_S.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_S.gguf new file mode 100644 index 0000000..e31514c --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7095c51a95dac017bc45e326afc745a8906a2e98f7270975b51ff293d5c66389 +size 3682325312 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_XS.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_XS.gguf new file mode 100644 index 0000000..17baf97 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45da32690c12d7ecf5f930d168707a11d47f1cb8cb484d3fbd1cf7a138d56c05 +size 3518747456 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ4_XS.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ4_XS.gguf new file mode 100644 index 0000000..407d8e3 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:385efbdba196108e0be0806b4dcaca5bc17a9b8c1ca1865643f4785d53734736 +size 4484363072 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q2_K.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q2_K.gguf new file mode 100644 index 0000000..400801c --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b900a8e48801136c01c97838a09002a5cb92df34240a1fd2e4cf7a64d9687564 +size 3179131712 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_L.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_L.gguf new file mode 100644 index 0000000..1b7b3c1 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5576619e51e68103319af2763b138de5419395910ba3cd4254ea0ed7439a6850 +size 4321956672 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_M.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_M.gguf new file mode 100644 index 0000000..2518f89 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e18569532052e187d35948f3cdf2232742d9ffaccdb8888ffa28d5a7485440 +size 4018918208 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_S.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_S.gguf new file mode 100644 index 0000000..838c767 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2fb4ebb8d74ddd8dbb731eb3301c31d93b93e2374de02b8a64fb9eb8526ae03 +size 3664499520 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_M.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_M.gguf new file mode 100644 index 0000000..1ceb9e3 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0fcffad97e93702028ca6053f3756af5307b54a4ffb071a843045a27a5d872f +size 4920734528 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_S.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_S.gguf new file mode 100644 index 0000000..bac341e --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9053976bb10664046af3f8642eec81810685193c0ea851382f701e5bbbead31c +size 4692669248 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_M.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_M.gguf new file mode 100644 index 0000000..4d41f9e --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14b6c848233ed6132cda7a073fffb17f1e7724064d96aa3877c3f7dfab13ee20 +size 5732987712 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_S.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_S.gguf new file mode 100644 index 0000000..71b29e2 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c1b346b1fba03e081223087507dc913c2b8dc86f7b6452e2c765fbd9fe814c9 +size 5599294272 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q6_K.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q6_K.gguf new file mode 100644 index 0000000..fd8f519 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82a2c652e58a2d49495401fd6d49283b282427284b4a2623a8dcd213c3d50574 +size 6596006720 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q8_0.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q8_0.gguf new file mode 100644 index 0000000..b737ffe --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72619380c236613b57081d34c210f7a93ce0d51a18123d475052c15db3174b1a +size 8540771136 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.f16.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.f16.gguf new file mode 100644 index 0000000..8bd8ec3 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a96694cbdc7e7ee7fea337d1673dd0a6d839c62474ed3a543488ab6b126bd6 +size 16068891456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..40d3f2a --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Magpie-Align/Llama-3-8B-Magpie-Align-v0.1 +datasets: +- princeton-nlp/llama3-ultrafeedback +- Magpie-Align/Magpie-Pro-MT-300K-v0.1 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- alignment-handbook +- axolotl +- trl +- dpo +- sft +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/Magpie-Align/Llama-3-8B-Magpie-Align-v0.1 + + +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-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO2-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO2.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. + +