commit 05c78228a24c2b5fb00ba3191fda1bdb9ca52e39 Author: ModelHub XC Date: Fri Jul 31 12:34:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..59c7857 --- /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-ExPO.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Instruct-8B-SimPO-ExPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_M.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_M.gguf new file mode 100644 index 0000000..93c601f --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f569ac56eab0912531a8a87cb36eed20acbe445d69b183ae1976aeda947b53a +size 3784823552 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_S.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_S.gguf new file mode 100644 index 0000000..ddcfdf9 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11826f410ac1e281007daedc401090215ddfa1dbd4c23cfbb62f20e715fd5583 +size 3682325248 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_XS.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_XS.gguf new file mode 100644 index 0000000..1503700 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8903ff87cdf487e17c1dc2f9b082fd1f56bbb794d85aba01f86acd0c7678e292 +size 3518747392 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.IQ4_XS.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.IQ4_XS.gguf new file mode 100644 index 0000000..20d0761 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd145fe230846c40064605ec8f2f190089596cbcb44d67f62268e0c95a10137e +size 4484363008 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q2_K.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q2_K.gguf new file mode 100644 index 0000000..6cb0119 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54aba52578576c9a26449f2087c359ae04114698a49474c1b8e7f618498a7410 +size 3179131648 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_L.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_L.gguf new file mode 100644 index 0000000..0f75f64 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43631cb9e4b05a6662fe3085e2f94810d483c979f080f8fc8a1a4e31b78df538 +size 4321956608 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_M.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_M.gguf new file mode 100644 index 0000000..c7a15dd --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47402f12eca95d471c7b44884d1c0adf8bc841e970de6acb62dca693fb53ed36 +size 4018918144 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_S.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_S.gguf new file mode 100644 index 0000000..d0de28f --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25722f1597b53c339eb127ae21a97ad1382232e2eb860bbe6f4f3f9122316f8b +size 3664499456 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_M.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_M.gguf new file mode 100644 index 0000000..87031f5 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac9ddef39ca5bb3aaa9e9b4b95029b982330800222b5125d56947b9b0a4628e +size 4920734464 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_S.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_S.gguf new file mode 100644 index 0000000..229dbb7 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c702009090b3430222ad21071dd29ca55e94dc5b1f7a30fee784e6dbaaf390 +size 4692669184 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_M.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_M.gguf new file mode 100644 index 0000000..be03b5c --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3202cfce5934e01785ec3b94d415b911ce2939e098bfd643a085801f8deacecb +size 5732987648 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_S.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_S.gguf new file mode 100644 index 0000000..bbca3b0 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb489e7b79b8364246780729ca52a3333dc99ff9819dd50aadfd86d9f2094b49 +size 5599294208 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q6_K.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q6_K.gguf new file mode 100644 index 0000000..4efa6d0 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c784be839938e9fec46c9cf393ff82d506aa3ee9d06a0ec221a531d8470d91 +size 6596006656 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.Q8_0.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.Q8_0.gguf new file mode 100644 index 0000000..afe1f8d --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ad345e8e255029ab0c1d2a0917dd2ea1ac86d0c311e6b3c394f80c0917c0c9 +size 8540771072 diff --git a/Llama-3-Instruct-8B-SimPO-ExPO.f16.gguf b/Llama-3-Instruct-8B-SimPO-ExPO.f16.gguf new file mode 100644 index 0000000..e0969e2 --- /dev/null +++ b/Llama-3-Instruct-8B-SimPO-ExPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ff360a0f2d0b261780e27b1dbd4acac9fc0bed9a2d5ab866f9bfa6c133c69b +size 16068891392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a9e1da9 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-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-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Instruct-8B-SimPO-ExPO-GGUF/resolve/main/Llama-3-Instruct-8B-SimPO-ExPO.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. + +