commit 80e46cab41c06313bb1b3bc654bd899e3fd4f4f9 Author: ModelHub XC Date: Mon Apr 27 09:02:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-dpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..278e747 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +llama3-8b-dpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-dpo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3ddd108 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: PeterJinGo/llama3-8b-dpo +language: +- en +library_name: transformers +model_name: llama3-8b-dpo +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/PeterJinGo/llama3-8b-dpo + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3-8b-dpo-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/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-dpo-GGUF/resolve/main/llama3-8b-dpo.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | + +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. + + diff --git a/llama3-8b-dpo.IQ4_XS.gguf b/llama3-8b-dpo.IQ4_XS.gguf new file mode 100644 index 0000000..81e94ce --- /dev/null +++ b/llama3-8b-dpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e35dae16268dd9ca5b28a35264ea8570188eaf704b328cb1030469866bc056a +size 4484363680 diff --git a/llama3-8b-dpo.Q2_K.gguf b/llama3-8b-dpo.Q2_K.gguf new file mode 100644 index 0000000..b6b2003 --- /dev/null +++ b/llama3-8b-dpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:230fcdfb58b636147281b955726ef59cc0ae3d14f7caa5f678a97d67da21727c +size 3179132320 diff --git a/llama3-8b-dpo.Q3_K_L.gguf b/llama3-8b-dpo.Q3_K_L.gguf new file mode 100644 index 0000000..0988354 --- /dev/null +++ b/llama3-8b-dpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09da2c3ea5606884da0cc188da0490fccff9e40cdfa425fe2f2070415ddc8e64 +size 4321957280 diff --git a/llama3-8b-dpo.Q3_K_M.gguf b/llama3-8b-dpo.Q3_K_M.gguf new file mode 100644 index 0000000..83b9b55 --- /dev/null +++ b/llama3-8b-dpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f44b0ef44eae5c8e18350f857fcb4cca6835b18e370908105950acaa4ea74fc6 +size 4018918816 diff --git a/llama3-8b-dpo.Q3_K_S.gguf b/llama3-8b-dpo.Q3_K_S.gguf new file mode 100644 index 0000000..d2f18a8 --- /dev/null +++ b/llama3-8b-dpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17ae001e6e4359dd0cbcfed1e4ae6d57b04bbf7929baab50ccd9ea4e181b6072 +size 3664500128 diff --git a/llama3-8b-dpo.Q4_K_M.gguf b/llama3-8b-dpo.Q4_K_M.gguf new file mode 100644 index 0000000..e319524 --- /dev/null +++ b/llama3-8b-dpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc334fd20ed476524d7ad727901dc36f285079ff5d5d698b80b4d108071bf9e +size 4920735136 diff --git a/llama3-8b-dpo.Q4_K_S.gguf b/llama3-8b-dpo.Q4_K_S.gguf new file mode 100644 index 0000000..f994707 --- /dev/null +++ b/llama3-8b-dpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691a4e67eb1f4a7eaa526af5bb173dffb64b3b6398a8755cfbd34c4dce74ecae +size 4692669856 diff --git a/llama3-8b-dpo.Q5_K_M.gguf b/llama3-8b-dpo.Q5_K_M.gguf new file mode 100644 index 0000000..cccdf59 --- /dev/null +++ b/llama3-8b-dpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e9b78a7de9d70ad56c111335cc901503377682213756e7799a2fb659a06d14 +size 5732988320 diff --git a/llama3-8b-dpo.Q5_K_S.gguf b/llama3-8b-dpo.Q5_K_S.gguf new file mode 100644 index 0000000..6033cc1 --- /dev/null +++ b/llama3-8b-dpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca4c4c7988056e70b62bbe600042f32a0f04de1158130f5c2c08eca0fed17fa6 +size 5599294880 diff --git a/llama3-8b-dpo.Q6_K.gguf b/llama3-8b-dpo.Q6_K.gguf new file mode 100644 index 0000000..7a835aa --- /dev/null +++ b/llama3-8b-dpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8c644ac9c9c867912dfbe3880aa026fb545623af90b68beb59c86231b6778c9 +size 6596007328 diff --git a/llama3-8b-dpo.Q8_0.gguf b/llama3-8b-dpo.Q8_0.gguf new file mode 100644 index 0000000..fb6b6b1 --- /dev/null +++ b/llama3-8b-dpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2022718d61574248322067e9d2ab2a2e7df33c08500a4060e6229620a1041a68 +size 8540771744