From d4a6d830c185032a3952dee4c94f07c434a1a53e Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 12 Apr 2026 21:24:07 +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/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF Source: Original Platform --- .gitattributes | 60 ++++++++++++++++ Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_M.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_S.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_M.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_S.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XS.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XXS.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_M.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_S.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XS.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XXS.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_NL.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_XS.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K_S.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_L.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_M.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_S.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_0.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_1.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_M.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_S.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_M.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_S.gguf | 3 + Qwen2.5-1.5B-Thinking-v1.1.i1-Q6_K.gguf | 3 + README.md | 82 ++++++++++++++++++++++ imatrix.dat | 3 + 27 files changed, 217 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_M.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_S.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_M.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_S.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XS.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XXS.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_M.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_S.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XS.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XXS.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_NL.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_XS.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K_S.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_L.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_M.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_S.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_0.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_1.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_M.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_S.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_M.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_S.gguf create mode 100644 Qwen2.5-1.5B-Thinking-v1.1.i1-Q6_K.gguf create mode 100644 README.md create mode 100644 imatrix.dat diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..07011a7 --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_M.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..13c547e --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6446351add13040fc85c6d7c1637ac8eecb381c6f6b8292b302bcb572095ba4 +size 464462208 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..1bce8ed --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b83923cc802aaef992929fb9572abb258d578fb422e538bea588a2ba81d9fc1b +size 436528512 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_M.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..d67a0f3 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af3fc4eea6d3cfe73c60df1aef19b36fbc894fcf865fd56992a68e353867ba8 +size 601055616 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..27fd60d --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a90d49ff754f42cf639645bb684c9cacb250c50201e376a27be7c6b2fae37213 +size 563810688 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XS.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2213d20 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a754841cfd1b722dc07fb8d3179b2a3dad69498e7f005807642c17b3ce6829c +size 550327680 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XXS.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..d26c08f --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16804920ed55165f4d87a68f6bd343452515f94b733d05f4bfc7961415b52597 +size 511018368 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_M.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..7dde123 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d16babbc94a1d94094ea978f7605f59991cf6c3d416ea5a2408b9ab1cec062 +size 776664960 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..e9f20ed --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0eec46eb26d21f9cc791841985c3029e308b390a92ec3c14261ac87ed616b17 +size 762407808 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XS.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..180d02d --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7631a185127b01f29b188baf1bba406eefb44b8f2e6a252137a1e21a995bb576 +size 731700096 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XXS.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..3ce5ad3 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:791f66fae4f04e412347a83907722a701bd5f19c29be09484f0638799c053173 +size 668793216 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_NL.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_NL.gguf new file mode 100644 index 0000000..79b001b --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:149814a3d083ad3e1de67a497abb098c55c2f451b58f0e8f51fb745a49501708 +size 936332160 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_XS.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8ad7650 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87c720d8e94f4c7a2b3166dac23febe4378520637f059a9773ea253800a7462e +size 895732608 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K.gguf new file mode 100644 index 0000000..e42b83c --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9896cdf50e0e999bd8aacb3f71ecb1f340773afe8ddd0144c0ed8351af01507 +size 676305792 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4d40a07 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b39f2e71bf3c17936d0052a63c6d21949ec42667f4f3730345409667abe70e8 +size 640136064 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_L.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..bc41939 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd45e275ba0179e31e4c918b5ccc17e501ffe94fa4225dcddae39baa34cca5b +size 880163712 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_M.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d6361dd --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c7807ca573ddc59c74e284c0aa2faf5539a7232f2954a2e48342fac0f114c4 +size 824179584 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..b6ba837 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6c71e8ab2567dc9ee53fc5fae603d9733d54f07783ec2b14db4d1f505f6aa9c +size 760945536 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_0.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_0.gguf new file mode 100644 index 0000000..c4ddd25 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b9b3d148ed0bd76a34107d9c06b2e85250a37f6cfa12e4562c7818b3414b0eb +size 937536384 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_1.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_1.gguf new file mode 100644 index 0000000..d3fd796 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eefe11379052b40d4dc5af6814a8729be70e541b30d1a945c76a08f0cf47287c +size 1016843136 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_M.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..84f25f0 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e0cdd2f0f3787a22ce7958564d4cb6f2900bc88f08f3b25dad85f8e4ae5ff9 +size 986049408 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..2e4b1ec --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6cc476f01146a837d1bb1462f05d2d1e588d46489d462fdf3c0f8ede40a108 +size 940313472 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_M.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..450a27a --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecfae2b8e024cfdb9cb36246a82e2043b47aa21e31055e0138ee8eb75658d786 +size 1125051264 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..0d363b3 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22eeb1c7faa86f3360f7945458c990560fd9486055ba171b0a81d7d9a099be82 +size 1098730368 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.i1-Q6_K.gguf b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q6_K.gguf new file mode 100644 index 0000000..059fd8a --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072d937b53193f558ff4435497d31bbb0e04817720e1ac2472fe080b901cd975 +size 1272740736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aed0d9d --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: justinj92/Qwen2.5-1.5B-Thinking-v1.1 +datasets: +- microsoft/orca-math-word-problems-200k +language: +- en +library_name: transformers +model_name: Qwen2.5-1.5B-Thinking-v1.1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/justinj92/Qwen2.5-1.5B-Thinking-v1.1 + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-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/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_S.gguf) | i1-IQ2_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ2_M.gguf) | i1-IQ2_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 1.0 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_0.gguf) | i1-Q4_0 | 1.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.0 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q4_1.gguf) | i1-Q4_1 | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.i1-Q6_K.gguf) | i1-Q6_K | 1.4 | 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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..260a3f5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b45b60d4c6feca4800ac95503a542bd2fe5bc23624795226abb3d263d7d465cf +size 2042201