commit 63f41ecffb461f7381912c497fe9002572fe27c4 Author: ModelHub XC Date: Sun Aug 30 10:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8db4ed7 --- /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 +OntoTune-sftdpo-Llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OntoTune-sftdpo-Llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OntoTune-sftdpo-Llama3-8B.IQ4_XS.gguf b/OntoTune-sftdpo-Llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..3109251 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c80bc349216bc28b8c43c7e829846c09007472a9421ba37c69db1d4463e24c8f +size 4484363296 diff --git a/OntoTune-sftdpo-Llama3-8B.Q2_K.gguf b/OntoTune-sftdpo-Llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..b9de990 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6f477bb59f0de637bb7d81a6ffd76a47e5de0353b8f136cee69dd7ab81e1eb +size 3179131936 diff --git a/OntoTune-sftdpo-Llama3-8B.Q3_K_L.gguf b/OntoTune-sftdpo-Llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..a94b448 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419a765f4d34b401f30ff46f72bd0d188b9c0236044cde22df098b0adf97a440 +size 4321956896 diff --git a/OntoTune-sftdpo-Llama3-8B.Q3_K_M.gguf b/OntoTune-sftdpo-Llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..23b44f3 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec49ebd1c7bb9d6b0d45311d469b45e3d5d5dbfb9e3f6fdfde8d476e06467c9c +size 4018918432 diff --git a/OntoTune-sftdpo-Llama3-8B.Q3_K_S.gguf b/OntoTune-sftdpo-Llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..d54b11b --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1b26010b58c2e8b6b616cb52d406fb29d42f28041d1d92b38ff7c52c7aa75fd +size 3664499744 diff --git a/OntoTune-sftdpo-Llama3-8B.Q4_K_M.gguf b/OntoTune-sftdpo-Llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..e180847 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ddde5ff281b22850b3e9fa740bbc0939496c10fe40d52a0cde0ed3faec3c41 +size 4920734752 diff --git a/OntoTune-sftdpo-Llama3-8B.Q4_K_S.gguf b/OntoTune-sftdpo-Llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..61acbc1 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bbe07450568007cbbb22fbb72240ca6340281754fffa568972a82cf2b468e5a +size 4692669472 diff --git a/OntoTune-sftdpo-Llama3-8B.Q5_K_M.gguf b/OntoTune-sftdpo-Llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..a69810d --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a4a867081a3c05cf626cde3ca453d666d56ba2a4c763ff213e6beb7ff5aba1b +size 5732987936 diff --git a/OntoTune-sftdpo-Llama3-8B.Q5_K_S.gguf b/OntoTune-sftdpo-Llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..f5dd809 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:313c5d720719a5c298341d05f470b12145a378e975107516b11191f7ab0ff5e2 +size 5599294496 diff --git a/OntoTune-sftdpo-Llama3-8B.Q6_K.gguf b/OntoTune-sftdpo-Llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..3078417 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af0d9768ae2e5893bea54b99aaf3d6b48c6b83cdc73e07ed2fe5a3b17732fa85 +size 6596006944 diff --git a/OntoTune-sftdpo-Llama3-8B.Q8_0.gguf b/OntoTune-sftdpo-Llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..5d8a174 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ae6c6adb1dd4c711d69212ac8c16794afd59c85706cbad3a45c39729659c44 +size 8540771360 diff --git a/OntoTune-sftdpo-Llama3-8B.f16.gguf b/OntoTune-sftdpo-Llama3-8B.f16.gguf new file mode 100644 index 0000000..5be9cc3 --- /dev/null +++ b/OntoTune-sftdpo-Llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b89ea0de59a0d6da548d3bc68ce2d40c19c8329018f6665e91a68e5570250a04 +size 16068891680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e1b20a3 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: zjukg/OntoTune-sftdpo-Llama3-8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zjukg/OntoTune-sftdpo-Llama3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OntoTune-sftdpo-Llama3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-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/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OntoTune-sftdpo-Llama3-8B-GGUF/resolve/main/OntoTune-sftdpo-Llama3-8B.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. + +