commit 77ee822d9f33e56fa6241b453e22530f994306f5 Author: ModelHub XC Date: Sat Jun 27 22:31:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-8B-SimPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..daead53 --- /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 +Llama3-8B-SimPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-8B-SimPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-8B-SimPO.IQ4_XS.gguf b/Llama3-8B-SimPO.IQ4_XS.gguf new file mode 100644 index 0000000..70b2ae6 --- /dev/null +++ b/Llama3-8B-SimPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9057a8be69ba2dadc9f9b33185e94ff26b48db6678e7eb0bb279e0f6aa3ed8f3 +size 4484363808 diff --git a/Llama3-8B-SimPO.Q2_K.gguf b/Llama3-8B-SimPO.Q2_K.gguf new file mode 100644 index 0000000..e16a3d2 --- /dev/null +++ b/Llama3-8B-SimPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ac738ea71d51d9f391d8d2e9d6a0d5942755726dd1ebe7759923751d3ce85fa +size 3179132448 diff --git a/Llama3-8B-SimPO.Q3_K_L.gguf b/Llama3-8B-SimPO.Q3_K_L.gguf new file mode 100644 index 0000000..afef617 --- /dev/null +++ b/Llama3-8B-SimPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5e006ef3cb19a1c95ad5d78641314fc6c79591c345cd7142b7bf77580810b0 +size 4321957408 diff --git a/Llama3-8B-SimPO.Q3_K_M.gguf b/Llama3-8B-SimPO.Q3_K_M.gguf new file mode 100644 index 0000000..8041e78 --- /dev/null +++ b/Llama3-8B-SimPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce2ac43800e354e91f559688625205440a18f38afce9f9c9d6e0f01f5e5c3cf +size 4018918944 diff --git a/Llama3-8B-SimPO.Q3_K_S.gguf b/Llama3-8B-SimPO.Q3_K_S.gguf new file mode 100644 index 0000000..0490532 --- /dev/null +++ b/Llama3-8B-SimPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0286e993653e3294ec906598f1c8df927a4dbbf6dfb3386a633ca6649b252b97 +size 3664500256 diff --git a/Llama3-8B-SimPO.Q4_K_M.gguf b/Llama3-8B-SimPO.Q4_K_M.gguf new file mode 100644 index 0000000..03ff3ac --- /dev/null +++ b/Llama3-8B-SimPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a9d876d20c73171b9f99acbb515ba11811ba45d4c72657e37794a1871ecabb +size 4920735264 diff --git a/Llama3-8B-SimPO.Q4_K_S.gguf b/Llama3-8B-SimPO.Q4_K_S.gguf new file mode 100644 index 0000000..8521775 --- /dev/null +++ b/Llama3-8B-SimPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be2e9d0aac9b00bd91539921a9e5d9c2f8cddcc90781328740c574ae2b3fa84d +size 4692669984 diff --git a/Llama3-8B-SimPO.Q5_K_M.gguf b/Llama3-8B-SimPO.Q5_K_M.gguf new file mode 100644 index 0000000..e2faeaa --- /dev/null +++ b/Llama3-8B-SimPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44824345a25a7ea61d8412f5adfd6eff570d509d3c5c142985ccfec7f4b02303 +size 5732988448 diff --git a/Llama3-8B-SimPO.Q5_K_S.gguf b/Llama3-8B-SimPO.Q5_K_S.gguf new file mode 100644 index 0000000..4f68717 --- /dev/null +++ b/Llama3-8B-SimPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f112b3e405f1fa09434b4da574872e6f2bc1958a6680a25c64de52780156b235 +size 5599295008 diff --git a/Llama3-8B-SimPO.Q6_K.gguf b/Llama3-8B-SimPO.Q6_K.gguf new file mode 100644 index 0000000..66abaaf --- /dev/null +++ b/Llama3-8B-SimPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce4db9452771f27e8bc6508dc07812ca13a054c083a2c8f6bac95153e3da68e3 +size 6596007456 diff --git a/Llama3-8B-SimPO.Q8_0.gguf b/Llama3-8B-SimPO.Q8_0.gguf new file mode 100644 index 0000000..a810a8b --- /dev/null +++ b/Llama3-8B-SimPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9433a9c25e00c634dd379f637e82c24fd73c798106d9ea8a67d71649bb188f +size 8540771872 diff --git a/Llama3-8B-SimPO.f16.gguf b/Llama3-8B-SimPO.f16.gguf new file mode 100644 index 0000000..24555f1 --- /dev/null +++ b/Llama3-8B-SimPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c39430b418c0497897158d512e6c1bbe77a9998ae935f0044c52d6c3a8618b +size 16068892192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..06d2411 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: RTO-RL/Llama3-8B-SimPO +datasets: +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/RTO-RL/Llama3-8B-SimPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3-8B-SimPO-GGUF).*** + +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/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-SimPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-8B-SimPO-GGUF/resolve/main/Llama3-8B-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. + +