From 364f5d15592f30a1d9a8a69ede0bdb10fae6b9ae Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 17 Oct 2026 21:46:20 +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-Swallow-8B-v0.5-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++ Llama-3.1-Swallow-8B-v0.5.i1-IQ1_M.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ1_S.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ2_M.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ2_S.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XS.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XXS.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ3_M.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ3_S.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XS.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XXS.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ4_NL.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-IQ4_XS.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q2_K.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q2_K_S.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_L.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_M.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_S.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q4_0.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q4_1.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_M.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_S.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_M.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_S.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.i1-Q6_K.gguf | 3 + Llama-3.1-Swallow-8B-v0.5.imatrix.gguf | 3 + README.md | 92 +++++++++++++++++++++++ 27 files changed, 227 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ1_M.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ1_S.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ2_M.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ2_S.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XS.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XXS.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ3_M.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ3_S.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XS.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XXS.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ4_NL.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-IQ4_XS.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q2_K.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q2_K_S.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_L.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_M.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_S.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q4_0.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q4_1.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_M.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_S.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_M.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_S.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.i1-Q6_K.gguf create mode 100644 Llama-3.1-Swallow-8B-v0.5.imatrix.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d4b0400 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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-Swallow-8B-v0.5.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.5.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ1_M.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ1_M.gguf new file mode 100644 index 0000000..e3c28c9 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:857feeaa81331c28a64a0d87daaf0ced5eedc20ecdee38bb913f09480412f73a +size 2161973216 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ1_S.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ1_S.gguf new file mode 100644 index 0000000..c13f913 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faba7b108f60804aee5d8edc5a7b4178db76723b39da439a56ee953c11be6536 +size 2019629024 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_M.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_M.gguf new file mode 100644 index 0000000..70ad224 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260b0d6f3385de0d15a919396e22d9b8293c8445d860163e620104d41ebafc2f +size 2948282336 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_S.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_S.gguf new file mode 100644 index 0000000..edc5f75 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:096be575613f084fa531a5a3fc39857a07f08a22f32ad0a025cb65a5ce660b62 +size 2758490080 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XS.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XS.gguf new file mode 100644 index 0000000..b8725a3 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dffc3840acca3e85c47976d4299f9e555c293b86dd1e5e5908bf54783e737acc +size 2605783008 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XXS.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..7806e11 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d794efb5315c7c9ad90cd5163412c2cc9daddf2285c4e099651c71e1e5e97530 +size 2399213536 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_M.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_M.gguf new file mode 100644 index 0000000..c9d53c9 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2482dfe5b796a60aa9f9f7e14381958d20a3cd2ecd2a723e61579a0af61ecb49 +size 3784824800 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_S.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_S.gguf new file mode 100644 index 0000000..5b71232 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49995fc2616aa3b1b31300a5545426f89990b67e1b91f5d91eb2b3b0d1cd5bdf +size 3682326496 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XS.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XS.gguf new file mode 100644 index 0000000..03c8e46 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ad6a65d30958ec14f66792a9f4dd5dd30f8fece59b6c7a2646ebdb7d65d708 +size 3518748640 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XXS.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..2b0ca2a --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c239daaf25b30dd6080d98ad2069793a0ec9cd3182eb7b4d6aedce5f657bad +size 3274913760 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ4_NL.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ4_NL.gguf new file mode 100644 index 0000000..a42e706 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7ca7c7d11e0028729426efef61e1178d49ab1bf9d5c62767a03c94568ceb248 +size 4677990368 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-IQ4_XS.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-IQ4_XS.gguf new file mode 100644 index 0000000..428b81f --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92411147fa6f82842815e3a7d4458b4899f5d8ba99d33d61fd3450db21419d2b +size 4447664096 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q2_K.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q2_K.gguf new file mode 100644 index 0000000..580d8f2 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3739e51010de79e07f7ca8c23b8f7ced26fe943cd11586d9f49f8be156e48986 +size 3179132896 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q2_K_S.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c1c6993 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38af11a92cd5697cc002c0be06c04f7fab47ed741c4999c4329cab56ab474664 +size 2988816352 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_L.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_L.gguf new file mode 100644 index 0000000..9fd1623 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ab72acbef93e9ffd062d734510122c3c788969cd1780c7f77846ea6ee0e8dc2 +size 4321957856 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_M.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f084616 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53523ed06779090dc992cd88502de63e9b36953be2f988b60b199b762c3f0055 +size 4018919392 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_S.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_S.gguf new file mode 100644 index 0000000..075c113 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:863eb4479fc14589d86c131f7ba7368cebfae94e8e6a9eec9feecf3eff435ea3 +size 3664500704 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q4_0.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q4_0.gguf new file mode 100644 index 0000000..4b6f80d --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d113af1969f94702de2af003eeba3346a1d2b9d351a2aee805aedadf742f31f4 +size 4675893216 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q4_1.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q4_1.gguf new file mode 100644 index 0000000..1224fb0 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b043e5ada03ce8caec9702e59c4892941b6449108a2439582aeafab9d042e92b +size 5130254304 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_M.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_M.gguf new file mode 100644 index 0000000..851e0e6 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1cb585b9f7bbb62754aa75ea56165921a5931a0c6b7f447380c1651c580a418 +size 4920735712 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_S.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8f82009 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdeb4e5e00dc3da55bf1ca40cd4e16054efe71ef8ca7e7b5a08c44cde21fccf1 +size 4692670432 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_M.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a76c445 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:936dd0a197c77af42e37e2e6b7aecd690531126ecab79258643e9345d0b09c35 +size 5732988896 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_S.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_S.gguf new file mode 100644 index 0000000..23ed8e4 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e5f55feb5833a5733c4f432dd77dafc06d825415a8dfd8917abdca141e99d0 +size 5599295456 diff --git a/Llama-3.1-Swallow-8B-v0.5.i1-Q6_K.gguf b/Llama-3.1-Swallow-8B-v0.5.i1-Q6_K.gguf new file mode 100644 index 0000000..2933368 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:711ebedac59fe0ef2e55606c3e340895144b66884b3a522e1dd81284b4496a73 +size 6596007904 diff --git a/Llama-3.1-Swallow-8B-v0.5.imatrix.gguf b/Llama-3.1-Swallow-8B-v0.5.imatrix.gguf new file mode 100644 index 0000000..bcb1760 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.5.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a93c2f648779fa0dc48033a2140960821918f7f2ab88cc0991be183d3aabbd +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..953e1cb --- /dev/null +++ b/README.md @@ -0,0 +1,92 @@ +--- +base_model: tokyotech-llm/Llama-3.1-Swallow-8B-v0.5 +datasets: +- tokyotech-llm/swallow-code +- tokyotech-llm/swallow-math +language: +- en +- ja +library_name: transformers +license: +- llama3.3 +- gemma +model_type: llama +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-v0.5 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-Swallow-8B-v0.5-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-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-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.5-i1-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.5.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +