commit 6442f45f688ab9d24dd95c0edb504d41bdc8e413 Author: ModelHub XC Date: Sat May 9 04:33:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-Instruct-8B-RSPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e0e1e79 --- /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-Instruct-8B-RSPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Instruct-8B-RSPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-Instruct-8B-RSPO.IQ4_XS.gguf b/Llama3-Instruct-8B-RSPO.IQ4_XS.gguf new file mode 100644 index 0000000..c58e05c --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d886ec1f846adadc2f9b859be61cba1a1a735152a773716e9b12b9f42bc4b25 +size 4484363392 diff --git a/Llama3-Instruct-8B-RSPO.Q2_K.gguf b/Llama3-Instruct-8B-RSPO.Q2_K.gguf new file mode 100644 index 0000000..aebee7f --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0092c4fb55d2c2c2d099fa5b650343f4f9cf4dfb5b11eef8e9d63eb61967d9c4 +size 3179132032 diff --git a/Llama3-Instruct-8B-RSPO.Q3_K_L.gguf b/Llama3-Instruct-8B-RSPO.Q3_K_L.gguf new file mode 100644 index 0000000..a7cea69 --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af51d4a9754c82db8acb04c39eb44c67a4fc9c8ab0fe888e9ecc30c9d3e2a3d +size 4321956992 diff --git a/Llama3-Instruct-8B-RSPO.Q3_K_M.gguf b/Llama3-Instruct-8B-RSPO.Q3_K_M.gguf new file mode 100644 index 0000000..e2f8e6f --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b03d4b3786591f79dfdda32cc0f9a184a3e30ce468e8168fdd654397a6c5e3a1 +size 4018918528 diff --git a/Llama3-Instruct-8B-RSPO.Q3_K_S.gguf b/Llama3-Instruct-8B-RSPO.Q3_K_S.gguf new file mode 100644 index 0000000..876607f --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a286b3cd550cc1647271527036b51d843e0a1507775f4fef93ec428e40bfd350 +size 3664499840 diff --git a/Llama3-Instruct-8B-RSPO.Q4_K_M.gguf b/Llama3-Instruct-8B-RSPO.Q4_K_M.gguf new file mode 100644 index 0000000..113f93f --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b03edcb01be47b81b09475631f8583d6ea63232f359f07ab74bc63a4e2b04d +size 4920734848 diff --git a/Llama3-Instruct-8B-RSPO.Q4_K_S.gguf b/Llama3-Instruct-8B-RSPO.Q4_K_S.gguf new file mode 100644 index 0000000..a6d46a7 --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3ab357f4cba4d2f2adb97aa9a7cd54d866864f1d33b117677a8efde038978c +size 4692669568 diff --git a/Llama3-Instruct-8B-RSPO.Q5_K_M.gguf b/Llama3-Instruct-8B-RSPO.Q5_K_M.gguf new file mode 100644 index 0000000..edf908c --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20b49d3ca0777ff28f8d069b63cfa2062ec0efda4a5a304011873ff1cd928f8 +size 5732988032 diff --git a/Llama3-Instruct-8B-RSPO.Q5_K_S.gguf b/Llama3-Instruct-8B-RSPO.Q5_K_S.gguf new file mode 100644 index 0000000..be9113c --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:767129bf1af8df55984583ebd4b2b4602688688e8b256e92b5ea849b2d755319 +size 5599294592 diff --git a/Llama3-Instruct-8B-RSPO.Q6_K.gguf b/Llama3-Instruct-8B-RSPO.Q6_K.gguf new file mode 100644 index 0000000..f52cf00 --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e4e0ed01a0c97680f6734fabe747026a1503698b788f9f00efafe7f5bace876 +size 6596007040 diff --git a/Llama3-Instruct-8B-RSPO.Q8_0.gguf b/Llama3-Instruct-8B-RSPO.Q8_0.gguf new file mode 100644 index 0000000..86e0398 --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9dcaa20646fb0c9e9cb55fc8e6b4a2e8622f779afa785a04451763bad25434a +size 8540771456 diff --git a/Llama3-Instruct-8B-RSPO.f16.gguf b/Llama3-Instruct-8B-RSPO.f16.gguf new file mode 100644 index 0000000..7b1def4 --- /dev/null +++ b/Llama3-Instruct-8B-RSPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a05baa6893b0e91026cb4ac1f9fc52096a10415177a03ea552f3a0062f30639 +size 16068891776 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8379160 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: li11111/Llama3-Instruct-8B-RSPO +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- pytorch +- llama-3 +--- +## About + + + + + + +static quants of https://huggingface.co/li11111/Llama3-Instruct-8B-RSPO + + +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-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Instruct-8B-RSPO-GGUF/resolve/main/Llama3-Instruct-8B-RSPO.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. + +