commit f926119ef8702b3460493496b19656ae81cf2e8a Author: ModelHub XC Date: Sat Apr 11 02:58:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..37610a9 --- /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-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_M.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_M.gguf new file mode 100644 index 0000000..c9570f4 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:309431dccaeb28bbed824dbc779adaf162c2843dd0359485ac3d5069a7a0af63 +size 3784824832 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_S.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_S.gguf new file mode 100644 index 0000000..29fe9af --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cdcf954f1dd20666556c1d5e581abaf8676c691712666bd94d93ee29982f63d +size 3682326528 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_XS.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_XS.gguf new file mode 100644 index 0000000..98f39b3 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78fc19363ca27d33e6bd2d788583fa1dd3b58a61ff380ad1b62da7905e39a81a +size 3518748672 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ4_XS.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ4_XS.gguf new file mode 100644 index 0000000..e0d92ed --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b024d27fc09e145616324c55bb0792c8797c0d650861b663c3b29844925b63b3 +size 4484364288 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q2_K.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q2_K.gguf new file mode 100644 index 0000000..45b61a9 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50420915c3bbb563111ca8130f294694e52f63abb6a050291256b7dc40efbbea +size 3179132928 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_L.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_L.gguf new file mode 100644 index 0000000..48ecd74 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa15cddc9f7b8dc35e8ae98500f8905d5404c20a4195cd45e3eaab58e974fab1 +size 4321957888 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_M.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_M.gguf new file mode 100644 index 0000000..096c1bd --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7255d0d6e025ff5d08e539b8aa23dddfc3963ef6b025c30aaa3695350147b648 +size 4018919424 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_S.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_S.gguf new file mode 100644 index 0000000..01f4e91 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f3be85145759cace4406ff0fbdff5a110d36488cadee37b2b4dc00330d3688 +size 3664500736 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_M.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_M.gguf new file mode 100644 index 0000000..44fe1b0 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5179b5c3df81de16a09ad9c26c6d641f8c95e3dbb6ea4f6d2ba01ebcbce08b +size 4920735744 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_S.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_S.gguf new file mode 100644 index 0000000..bec56be --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:148fab4e38ee6c49f70a6ad285316713aded426827bef99f066feeab1b6dc90f +size 4692670464 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_M.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_M.gguf new file mode 100644 index 0000000..b672227 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a015ab432bdd8efbeacaae02cc5d42efd25b8bbd43f3b8672576e31bdce6d73b +size 5732988928 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_S.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_S.gguf new file mode 100644 index 0000000..1346840 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56fc8efdcfa8cfe071be791dbb1e5da5cf51cb949cd1b28f10dcd6afd029ad31 +size 5599295488 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q6_K.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q6_K.gguf new file mode 100644 index 0000000..8b48773 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cfdbbb1d79ef732a769710b85d87a3c78394c4e848edc476f29b1e290a903b1 +size 6596007936 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q8_0.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q8_0.gguf new file mode 100644 index 0000000..c2a6b62 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd17098c2427f53eb34f0d039a501e97a15b2b370e2f389c9e515f8e248b35c +size 8540772352 diff --git a/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.f16.gguf b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.f16.gguf new file mode 100644 index 0000000..2610a40 --- /dev/null +++ b/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dff632318b369b24320b636aa48b01a1e9349ad934921b2fe294f0bf8dd5d19f +size 16068892672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8d026e0 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Magpie-Align/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05 +datasets: +- princeton-nlp/llama3-ultrafeedback-armorm +language: +- en +library_name: transformers +license: llama3.1 +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-3.1-8B-Magpie-SFT-950K-UltraDPO-05 + + +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-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05-GGUF/resolve/main/Llama-3.1-8B-Magpie-SFT-950K-UltraDPO-05.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. + +