commit 5a2646cee94041703250f23fa7f1058bb9072915 Author: ModelHub XC Date: Thu Jul 30 00:49:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3d1b484 --- /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-UltraDPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_M.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_M.gguf new file mode 100644 index 0000000..ae5bdfb --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:958950f5ceeb000805012ac8c31c570490777659b27d4572a31eb61b92df8091 +size 3784823616 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_S.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_S.gguf new file mode 100644 index 0000000..b0562b3 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ceace6caa5aa54a5d89324838ac519800fada3278e53ea0c3683a221ff2459 +size 3682325312 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_XS.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_XS.gguf new file mode 100644 index 0000000..6e1820b --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d8475d72fca2cc32b44e6c7c661fc000535b4a0f19c2116ceb100c2bbd46ef +size 3518747456 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ4_XS.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ4_XS.gguf new file mode 100644 index 0000000..678937f --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edecd60ae658115f1ba0556c809c01bddb39c7e8e6055d09de74e1554707e971 +size 4484363072 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q2_K.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q2_K.gguf new file mode 100644 index 0000000..bc47362 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f816edeb9f203c84d659e882330ffa0b25e7491352fe631659561cd3a6807b90 +size 3179131712 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_L.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_L.gguf new file mode 100644 index 0000000..3e4996c --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9a4ebd00196f411896a78ce2722e4775d843bce4a96da0bc82ddc11b6a713e +size 4321956672 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_M.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_M.gguf new file mode 100644 index 0000000..3c6b732 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be2f641f03dd01258c787a56baad80c2b4e5839fef10a3f3a0971a929dc2705 +size 4018918208 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_S.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_S.gguf new file mode 100644 index 0000000..9d204f7 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01edb0ba6d24deaa00a7c90048c1a244ab595ced20406e5c4908f5012c8c4514 +size 3664499520 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_M.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_M.gguf new file mode 100644 index 0000000..102f235 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d11d65676a995e5794d154749806a1e01d5950378481608e90f4de17af2adb5 +size 4920734528 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_S.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_S.gguf new file mode 100644 index 0000000..766eeb8 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ddbeb8d8f99c15d52cbb55a4d21568a736a0bada34a0c5a348f516d55577a6 +size 4692669248 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_M.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_M.gguf new file mode 100644 index 0000000..8653c5e --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ada21a0c580493b3ae7f54fe496675f0a0adb6318ae9b427c27a6e5d7d6d3c +size 5732987712 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_S.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_S.gguf new file mode 100644 index 0000000..d703d54 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d79f5abcb7125112cc1e8d28d93f2e4346244c91242c358c5a5a0b7b46760ca +size 5599294272 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q6_K.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q6_K.gguf new file mode 100644 index 0000000..77e156e --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ad8c7581c963ece8cf13cf742d9aa2725d56e73a09db12b40de46712cab825d +size 6596006720 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q8_0.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q8_0.gguf new file mode 100644 index 0000000..4748b50 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed714aff01a135911ab24cf7ec8897a5cb52f2a5eef2f87b369e3bf91c61ce9 +size 8540771136 diff --git a/Llama-3-8B-Magpie-Pro-MT-UltraDPO.f16.gguf b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.f16.gguf new file mode 100644 index 0000000..9fad649 --- /dev/null +++ b/Llama-3-8B-Magpie-Pro-MT-UltraDPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a532393189beddf2e58513d5112c3cacca2f0c3a14ca7296e92cdcd514a2067 +size 16068891456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..50ed59c --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Magpie-Align/Llama-3-8B-Magpie-Pro-MT-UltraDPO +datasets: +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- alignment-handbook +- trl +- dpo +- generated_from_trainer +- trl +- dpo +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/Magpie-Align/Llama-3-8B-Magpie-Pro-MT-UltraDPO + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-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/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Magpie-Pro-MT-UltraDPO-GGUF/resolve/main/Llama-3-8B-Magpie-Pro-MT-UltraDPO.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. + +