commit f39511ddda6fe17fad49ed42d039a1ac2bb653e0 Author: ModelHub XC Date: Sun Jul 12 10:46:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..56dc2f3 --- /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 +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.f16.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5e29a70 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: mlfoundations-dev/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- trl +- dpo +- llama-factory +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/mlfoundations-dev/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b + + +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/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b-GGUF/resolve/main/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.IQ4_XS.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.IQ4_XS.gguf new file mode 100644 index 0000000..af4622a --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195a8923c70b86602061f6498e676dbf92c70427988b37763da5c43011124478 +size 4484364448 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q2_K.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q2_K.gguf new file mode 100644 index 0000000..e8befc3 --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32fec1719a2d9649c2102d2bd6ba7b0b0ad777f4d8745a59984b30ab0e74716b +size 3179133088 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_L.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_L.gguf new file mode 100644 index 0000000..4593019 --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b17739461912f7fa1546f6fb3521c17a2a206e9dee58923b4c80a25e79f02ca +size 4321958048 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_M.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_M.gguf new file mode 100644 index 0000000..5a94d45 --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb954e9c318091e70608997a5a95bff8eed4241af383d116bb9fd1a69bde9c92 +size 4018919584 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_S.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_S.gguf new file mode 100644 index 0000000..8dfabd9 --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f110fd0538ede792dc3017a34282c014be8da69f086c26af86dbb2975b0f5017 +size 3664500896 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_M.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_M.gguf new file mode 100644 index 0000000..9f32f18 --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c44624df65b2d2e2ad8e5a1067312b33296dd5efb86ebb24e7062ad7b824f441 +size 4920735904 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_S.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_S.gguf new file mode 100644 index 0000000..e8c9b58 --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5741f49a10bd83ea205994e16d2c639cec68d2fa7be636a79d043095a2de9128 +size 4692670624 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_M.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_M.gguf new file mode 100644 index 0000000..04e30ee --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3007e028c213f405555ae1da3200b4f9ef6afd154dd4d71757a51db44c69f520 +size 5732989088 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_S.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_S.gguf new file mode 100644 index 0000000..e2dfb0c --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9078e402e4402a90b7173de41127bb8b92dd72715bde73279b03946fe84c4f0f +size 5599295648 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q6_K.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q6_K.gguf new file mode 100644 index 0000000..ce8617d --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e04c41ab88b3d6a7df86a057f2eab717ea3ce8496374e705431a6b89df91dd +size 6596008096 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q8_0.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q8_0.gguf new file mode 100644 index 0000000..afc7e4a --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7944bd67cc6b5016e210035645f9aa0a6e0440afc6df3588a6e5bc850b03160b +size 8540772512 diff --git a/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.f16.gguf b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.f16.gguf new file mode 100644 index 0000000..b6b072d --- /dev/null +++ b/simpo-oh-dcft-v3.1-llama-3.1-nemotron-70b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbfb4b29062846a6da780d675ea39d219c8bef694db75f2e0e17058ae412ed9a +size 16068892832