commit 9756a25724de5f85f1a41e44ef5bbc62a59e1e09 Author: ModelHub XC Date: Fri Apr 10 21:17:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Instruct-8B-SimPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9c6c8a0 --- /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-Instruct-8B-SimPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Instruct-8B-SimPO.IQ3_M.gguf b/Llama-3-Instruct-8B-SimPO.IQ3_M.gguf new file mode 100644 index 0000000..b94505c --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ddc848128711c83798b26d843753fd6f22c94b023052b8def219401a1a7f5c +size 3784823584 diff --git a/Llama-3-Instruct-8B-SimPO.IQ3_S.gguf b/Llama-3-Instruct-8B-SimPO.IQ3_S.gguf new file mode 100644 index 0000000..3c34693 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcbfea84f8fa9da4d766e7ce1e97cfafcb11ff4356545ae9c38658ee698fc7e5 +size 3682325280 diff --git a/Llama-3-Instruct-8B-SimPO.IQ3_XS.gguf b/Llama-3-Instruct-8B-SimPO.IQ3_XS.gguf new file mode 100644 index 0000000..ae3eea4 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3259c451dd4976320388d9afd15c65c97a513ceaea508fbc3c5a38e76e5c7f +size 3518747424 diff --git a/Llama-3-Instruct-8B-SimPO.IQ4_XS.gguf b/Llama-3-Instruct-8B-SimPO.IQ4_XS.gguf new file mode 100644 index 0000000..2ad28c2 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4513bbc1b8345ae101ab86c2649704e43671c970c2b7d0259dc538686868aa8 +size 4484363040 diff --git a/Llama-3-Instruct-8B-SimPO.Q2_K.gguf b/Llama-3-Instruct-8B-SimPO.Q2_K.gguf new file mode 100644 index 0000000..c692bf3 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b49f8f834a85d87e3405bce4844c5283275d8c0c673c4b4b4bac94e93934dd3a +size 3179131680 diff --git a/Llama-3-Instruct-8B-SimPO.Q3_K_L.gguf b/Llama-3-Instruct-8B-SimPO.Q3_K_L.gguf new file mode 100644 index 0000000..7babb29 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc19c5fc5c929d77f58fe7396baa63136bb58878a0131c346afafa96cad8c8b2 +size 4321956640 diff --git a/Llama-3-Instruct-8B-SimPO.Q3_K_M.gguf b/Llama-3-Instruct-8B-SimPO.Q3_K_M.gguf new file mode 100644 index 0000000..7e342ad --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be737bc8f05ed8e74a6568725bbff2722657e65e578419ce804c71cca8a51fe1 +size 4018918176 diff --git a/Llama-3-Instruct-8B-SimPO.Q3_K_S.gguf b/Llama-3-Instruct-8B-SimPO.Q3_K_S.gguf new file mode 100644 index 0000000..5c74ef1 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896094d850d824a981c880c0f12c97e42f1c60079459f5c458727838910798c1 +size 3664499488 diff --git a/Llama-3-Instruct-8B-SimPO.Q4_K_M.gguf b/Llama-3-Instruct-8B-SimPO.Q4_K_M.gguf new file mode 100644 index 0000000..b2949f4 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3895b62a8d04808965091b493893e94c336d043288b08fdb8bd4aecb82c7589 +size 4920734496 diff --git a/Llama-3-Instruct-8B-SimPO.Q4_K_S.gguf b/Llama-3-Instruct-8B-SimPO.Q4_K_S.gguf new file mode 100644 index 0000000..21bc3d4 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90fe6fea030c7102795d6f3998a9048a1c5b72f0cfc636875b3753b141c21015 +size 4692669216 diff --git a/Llama-3-Instruct-8B-SimPO.Q5_K_M.gguf b/Llama-3-Instruct-8B-SimPO.Q5_K_M.gguf new file mode 100644 index 0000000..450a40b --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3614194a431d5b3ba7b068fe5cba60b4c2bcd74cd06738c3cdf47bfbc37fcf9f +size 5732987680 diff --git a/Llama-3-Instruct-8B-SimPO.Q5_K_S.gguf b/Llama-3-Instruct-8B-SimPO.Q5_K_S.gguf new file mode 100644 index 0000000..213c44f --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd6b25374add0b47354b6d646fe102a263066f340716cd6c6c796a58398fa1c7 +size 5599294240 diff --git a/Llama-3-Instruct-8B-SimPO.Q6_K.gguf b/Llama-3-Instruct-8B-SimPO.Q6_K.gguf new file mode 100644 index 0000000..6b938f7 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0efc3497b8e147eb42e6cdf99a9978c3bc0f5891159e7444f68fa1bc5e78f284 +size 6596006688 diff --git a/Llama-3-Instruct-8B-SimPO.Q8_0.gguf b/Llama-3-Instruct-8B-SimPO.Q8_0.gguf new file mode 100644 index 0000000..76bf60b --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1c1fc9c6b7c55637830143d2bbb8f64c30987fe5830e04596167714b60e0c0 +size 8540771104 diff --git a/Llama-3-Instruct-8B-SimPO.f16.gguf b/Llama-3-Instruct-8B-SimPO.f16.gguf new file mode 100644 index 0000000..8149d83 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d6a481045648eb9e617545db3a3e9a05554308d5954a14a1967005fab37d3a +size 16068891424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..16af9e7 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: princeton-nlp/Llama-3-Instruct-8B-SimPO +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/princeton-nlp/Llama-3-Instruct-8B-SimPO + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-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-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO.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. + +