From fcbb7649f798e8dd4ed268cfff9ca9de4d27e4d8 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 7 Jul 2026 21:34:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF Source: Original Platform --- .gitattributes | 47 ++++++++++++++++++++ LLaMA-3.1-8B-LongRLVR.IQ4_XS.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q2_K.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q3_K_L.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q3_K_M.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q3_K_S.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q4_K_M.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q4_K_S.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q5_K_M.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q5_K_S.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q6_K.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.Q8_0.gguf | 3 ++ LLaMA-3.1-8B-LongRLVR.f16.gguf | 3 ++ README.md | 71 +++++++++++++++++++++++++++++++ 14 files changed, 154 insertions(+) create mode 100644 .gitattributes create mode 100644 LLaMA-3.1-8B-LongRLVR.IQ4_XS.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q2_K.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q3_K_L.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q3_K_M.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q3_K_S.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q4_K_M.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q4_K_S.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q5_K_M.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q5_K_S.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q6_K.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.Q8_0.gguf create mode 100644 LLaMA-3.1-8B-LongRLVR.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0f2c5c0 --- /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 +LLaMA-3.1-8B-LongRLVR.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-LongRLVR.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA-3.1-8B-LongRLVR.IQ4_XS.gguf b/LLaMA-3.1-8B-LongRLVR.IQ4_XS.gguf new file mode 100644 index 0000000..80df621 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b676291cd9a0efdc1d2c40ad144617c8887606bb0119a43b6bc44f4589a283f +size 4484367872 diff --git a/LLaMA-3.1-8B-LongRLVR.Q2_K.gguf b/LLaMA-3.1-8B-LongRLVR.Q2_K.gguf new file mode 100644 index 0000000..c9979e8 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b672eb8972c144c490062ed4458db20d8886d26c779f9269f0946a3caec83292 +size 3179136512 diff --git a/LLaMA-3.1-8B-LongRLVR.Q3_K_L.gguf b/LLaMA-3.1-8B-LongRLVR.Q3_K_L.gguf new file mode 100644 index 0000000..ab169a4 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da63d77d4b294af4e5d6b434716b28d604fdbe75b4fd63af3e745c0849121d24 +size 4321961472 diff --git a/LLaMA-3.1-8B-LongRLVR.Q3_K_M.gguf b/LLaMA-3.1-8B-LongRLVR.Q3_K_M.gguf new file mode 100644 index 0000000..71fbb17 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eff4e3e7cc4dea97429b7bf2cf7177300544c9a8752890b18efdaa885b1aad6b +size 4018923008 diff --git a/LLaMA-3.1-8B-LongRLVR.Q3_K_S.gguf b/LLaMA-3.1-8B-LongRLVR.Q3_K_S.gguf new file mode 100644 index 0000000..88d147c --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbf4ce2babb08fe6a2b38703c65ad9446d808f263f2d4c2059c4ae7d29061b6d +size 3664504320 diff --git a/LLaMA-3.1-8B-LongRLVR.Q4_K_M.gguf b/LLaMA-3.1-8B-LongRLVR.Q4_K_M.gguf new file mode 100644 index 0000000..0ca6ed3 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecfda94c1f1d023c0528b969a0fdde47d0cc09e78298f9b425f0f67fc5e21b40 +size 4920739328 diff --git a/LLaMA-3.1-8B-LongRLVR.Q4_K_S.gguf b/LLaMA-3.1-8B-LongRLVR.Q4_K_S.gguf new file mode 100644 index 0000000..4bdade6 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236bca202840ab00c4462766d1af23056ab21bce4d7542cba10f25537be1fc86 +size 4692674048 diff --git a/LLaMA-3.1-8B-LongRLVR.Q5_K_M.gguf b/LLaMA-3.1-8B-LongRLVR.Q5_K_M.gguf new file mode 100644 index 0000000..63c5519 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a894c732fcebe96d20d1e066538188a6b35b2aba4abbd92373841f0fd7de3e1e +size 5732992512 diff --git a/LLaMA-3.1-8B-LongRLVR.Q5_K_S.gguf b/LLaMA-3.1-8B-LongRLVR.Q5_K_S.gguf new file mode 100644 index 0000000..dd891d8 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af7f301f23326c36e857e86cc2ef4b30ad3a99dc489c05f3adf50ba924b624a8 +size 5599299072 diff --git a/LLaMA-3.1-8B-LongRLVR.Q6_K.gguf b/LLaMA-3.1-8B-LongRLVR.Q6_K.gguf new file mode 100644 index 0000000..8c6f3a4 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c361d0f07ceb29b4600417aa27c3c6c2bbfe440930ec74056959ef9a0432b311 +size 6596011520 diff --git a/LLaMA-3.1-8B-LongRLVR.Q8_0.gguf b/LLaMA-3.1-8B-LongRLVR.Q8_0.gguf new file mode 100644 index 0000000..7128cb7 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d96d9a8d52a66d10cbac3feea41789694eabcde6668c59431a38f035aecf93f1 +size 8540775936 diff --git a/LLaMA-3.1-8B-LongRLVR.f16.gguf b/LLaMA-3.1-8B-LongRLVR.f16.gguf new file mode 100644 index 0000000..4448b18 --- /dev/null +++ b/LLaMA-3.1-8B-LongRLVR.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733fa54a3c47c787862a7e4c88e07129c448fa966044964899ce671f751a6b01 +size 16068896256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..253587a --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Guanzheng/LLaMA-3.1-8B-LongRLVR +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Guanzheng/LLaMA-3.1-8B-LongRLVR + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLaMA-3.1-8B-LongRLVR-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-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-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-LongRLVR-GGUF/resolve/main/LLaMA-3.1-8B-LongRLVR.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. + +