From 81962c6024a1886a040e04329c09a0467cfb01c2 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 30 May 2026 12:21:16 +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: duyntnet/Qwen2.5-Coder-7B-Instruct-imatrix-GGUF Source: Original Platform --- .gitattributes | 62 ++++++++++++++ Qwen2.5-Coder-7B-Instruct-IQ1_M.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ1_S.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ2_M.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ2_S.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ2_XS.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ2_XXS.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ3_M.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ3_S.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ3_XS.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ3_XXS.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ4_NL.gguf | 3 + Qwen2.5-Coder-7B-Instruct-IQ4_XS.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q2_K.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q2_K_S.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q3_K_L.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q3_K_M.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q3_K_S.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q4_0.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q4_1.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q4_K_S.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q5_0.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q5_1.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q5_K_M.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q5_K_S.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q6_K.gguf | 3 + Qwen2.5-Coder-7B-Instruct-Q8_0.gguf | 3 + README.md | 109 +++++++++++++++++++++++++ 29 files changed, 252 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ1_M.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ1_S.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ2_M.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ2_S.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ2_XS.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ2_XXS.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ3_M.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ3_S.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ3_XS.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ3_XXS.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ4_NL.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-IQ4_XS.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q2_K.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q2_K_S.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q3_K_L.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q3_K_M.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q3_K_S.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q4_0.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q4_1.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q4_K_S.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q5_0.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q5_1.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q5_K_M.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q5_K_S.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q6_K.gguf create mode 100644 Qwen2.5-Coder-7B-Instruct-Q8_0.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f2b9471 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,62 @@ +*.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 +Qwen2.5-Coder-7B-Instruct-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-7B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Coder-7B-Instruct-IQ1_M.gguf b/Qwen2.5-Coder-7B-Instruct-IQ1_M.gguf new file mode 100644 index 0000000..d80b8f3 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7bd45d04e42ac8eec774ca6a745b8d2fd66e7ccf4a9da6c04ac91968bf16c85 +size 2042197152 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ1_S.gguf b/Qwen2.5-Coder-7B-Instruct-IQ1_S.gguf new file mode 100644 index 0000000..e3c6cef --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:596dae781245e65b37b452c1475b5871c4486c00deebea51d692dddb9d17a08b +size 1903668384 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ2_M.gguf b/Qwen2.5-Coder-7B-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..c1b8a3a --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7246b8e6e6604700268b89f0bdbbeff5f23be90b87b285fa9734c5c489e12d3 +size 2780343456 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ2_S.gguf b/Qwen2.5-Coder-7B-Instruct-IQ2_S.gguf new file mode 100644 index 0000000..997a0db --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf02648fab3a8a73d86025ca9c03299b508448199846d4a48fafcfc9a2b4447 +size 2595638432 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ2_XS.gguf b/Qwen2.5-Coder-7B-Instruct-IQ2_XS.gguf new file mode 100644 index 0000000..1af19a4 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d3e8f4b4c88f1be837540b0cebdfaf451d9352915214a7a410aa5a5ec0453f0 +size 2469022880 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ2_XXS.gguf b/Qwen2.5-Coder-7B-Instruct-IQ2_XXS.gguf new file mode 100644 index 0000000..74fbbc6 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ef5d11082d774fa47e38b4dd43516862ddd7b82adc532513ef091d21520a2ed +size 2273078432 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ3_M.gguf b/Qwen2.5-Coder-7B-Instruct-IQ3_M.gguf new file mode 100644 index 0000000..9beb9fb --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:851af6af5d3d21c7377efca571830868886e8a096584df45b109c414414522a9 +size 3574013088 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ3_S.gguf b/Qwen2.5-Coder-7B-Instruct-IQ3_S.gguf new file mode 100644 index 0000000..587ef78 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17547af54d54c4871b8cc1232150f53b5b779b8cc138ab10c967e3990d335135 +size 3499193504 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ3_XS.gguf b/Qwen2.5-Coder-7B-Instruct-IQ3_XS.gguf new file mode 100644 index 0000000..5a4bea7 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d37b78ea47ecab4807ba0346159191dc5df8ccd1aa47bebfd8cb16645dc413b4 +size 3346257056 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ3_XXS.gguf b/Qwen2.5-Coder-7B-Instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..335b224 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe921676a0bb893b423ca72dad27c30bb4eded7f50e57fa6b2d0a80777e46ead +size 3114515616 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ4_NL.gguf b/Qwen2.5-Coder-7B-Instruct-IQ4_NL.gguf new file mode 100644 index 0000000..b1c3f25 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dafad5f6661d94fdb1f0025a492de69999653e4f9a61f9c978508d4155e30ce3 +size 4437814432 diff --git a/Qwen2.5-Coder-7B-Instruct-IQ4_XS.gguf b/Qwen2.5-Coder-7B-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..e7368ee --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f823fce748ae5ca14e568e4ed41b26812a391d0801e2805ae307e13c223f4294 +size 4218473632 diff --git a/Qwen2.5-Coder-7B-Instruct-Q2_K.gguf b/Qwen2.5-Coder-7B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..17849d4 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f8dd4ee4dc1c5c0aea694d1aa0f2738253a9bb2bd800cb78299ea72a1c8d7e0 +size 3015941280 diff --git a/Qwen2.5-Coder-7B-Instruct-Q2_K_S.gguf b/Qwen2.5-Coder-7B-Instruct-Q2_K_S.gguf new file mode 100644 index 0000000..7e1c743 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87e564898bcdebb10ea6a280030b51d98e9ebbae4c2493a0adbcb650fbed05f6 +size 2834074784 diff --git a/Qwen2.5-Coder-7B-Instruct-Q3_K_L.gguf b/Qwen2.5-Coder-7B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..12f7eaf --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50573e8a56a71ad802a366d4f7953288cebd7612c19374d2e97375b4e4504a4c +size 4088460448 diff --git a/Qwen2.5-Coder-7B-Instruct-Q3_K_M.gguf b/Qwen2.5-Coder-7B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..6983b00 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eec65c103ac34314cca4369651fa00b732e86076b45f10c47935a5c2364c16c +size 3808392352 diff --git a/Qwen2.5-Coder-7B-Instruct-Q3_K_S.gguf b/Qwen2.5-Coder-7B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..542ebb2 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8853d5d6c7fa6cbd7d14503e183de8dcddb208fcb10da3dfa18c879b3ca96d90 +size 3492369568 diff --git a/Qwen2.5-Coder-7B-Instruct-Q4_0.gguf b/Qwen2.5-Coder-7B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..45f65fe --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816a631fd8e796cbfadf8e486add6b1725c51399d7367224560976bbb88ec8fa +size 4444122272 diff --git a/Qwen2.5-Coder-7B-Instruct-Q4_1.gguf b/Qwen2.5-Coder-7B-Instruct-Q4_1.gguf new file mode 100644 index 0000000..4e65884 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd2c1fb817bdec1599c3e2c378c39a6e4a754bb1709ee560b6a5b76760f1140 +size 4873284768 diff --git a/Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf b/Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..a77aff2 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d19d30d2b8c219cd2022d75c76eae79b9f7532917f851001cd0aa087e0b2c7e +size 4683074720 diff --git a/Qwen2.5-Coder-7B-Instruct-Q4_K_S.gguf b/Qwen2.5-Coder-7B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..7b99a46 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c4d8742f0f622980c7470a3d4204a1ef94c4671ad9d5d01bba2a90ac2184903 +size 4457770144 diff --git a/Qwen2.5-Coder-7B-Instruct-Q5_0.gguf b/Qwen2.5-Coder-7B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..c96c520 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5c1094db9e018003818fc285627153c471ed0199c19f445a783910fcf6a7b45 +size 5327908000 diff --git a/Qwen2.5-Coder-7B-Instruct-Q5_1.gguf b/Qwen2.5-Coder-7B-Instruct-Q5_1.gguf new file mode 100644 index 0000000..c1a28f1 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418dc072833a54a686771638905d25258bbd608246cacf88fd7710964988e10f +size 5757070496 diff --git a/Qwen2.5-Coder-7B-Instruct-Q5_K_M.gguf b/Qwen2.5-Coder-7B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..cd53cc4 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f75ae8efe4d15917c885350ea70f49535222c47e73945c76d8f76eb242864c0 +size 5444832416 diff --git a/Qwen2.5-Coder-7B-Instruct-Q5_K_S.gguf b/Qwen2.5-Coder-7B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..f6f2fa2 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b51b82adad74c09c1d6d1c25a49b8445d99db56945d22bba0dc2c8f80fd99d +size 5315177632 diff --git a/Qwen2.5-Coder-7B-Instruct-Q6_K.gguf b/Qwen2.5-Coder-7B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..e8a8d80 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:018ebbc3c88805e83309f80da3931474b40323180b911eba206a31f8b2110e33 +size 6254199968 diff --git a/Qwen2.5-Coder-7B-Instruct-Q8_0.gguf b/Qwen2.5-Coder-7B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..93773e9 --- /dev/null +++ b/Qwen2.5-Coder-7B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ed1587d44957b1d0469454783e735eb1c4f460398d841991c7c8c9f7131238 +size 8098526368 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2ecb591 --- /dev/null +++ b/README.md @@ -0,0 +1,109 @@ +--- +license: other +language: +- en +pipeline_tag: text-generation +inference: false +tags: +- transformers +- gguf +- imatrix +- Qwen2.5-Coder-7B-Instruct +--- +Quantizations of https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct + + +### Inference Clients/UIs +* [llama.cpp](https://github.com/ggerganov/llama.cpp) +* [KoboldCPP](https://github.com/LostRuins/koboldcpp) +* [text-generation-webui](https://github.com/oobabooga/text-generation-webui) +* [ollama](https://github.com/ollama/ollama) + + +--- + +# From original readme + +Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). For Qwen2.5-Coder, we release three base language models and instruction-tuned language models, 1.5, 7 and 32 (coming soon) billion parameters. Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: + +- Significantly improvements in **code generation**, **code reasoning** and **code fixing**. Base on the strong Qwen2.5, we scale up the training tokens into 5.5 trillion including source code, text-code grounding, Synthetic data, etc. +- A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies. +- **Long-context Support** up to 128K tokens. + +**This repo contains the instruction-tuned 7B Qwen2.5-Coder model**, which has the following features: +- Type: Causal Language Models +- Training Stage: Pretraining & Post-training +- Architecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias +- Number of Parameters: 7.61B +- Number of Paramaters (Non-Embedding): 6.53B +- Number of Layers: 28 +- Number of Attention Heads (GQA): 28 for Q and 4 for KV +- Context Length: Full 131,072 tokens + - Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2.5 for handling long texts. + +For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-coder/), [GitHub](https://github.com/QwenLM/Qwen2.5-Coder), [Documentation](https://qwen.readthedocs.io/en/latest/), [Arxiv](https://arxiv.org/abs/2409.12186). + +## Requirements + +The code of Qwen2.5-Coder has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`. + +With `transformers<4.37.0`, you will encounter the following error: +``` +KeyError: 'qwen2' +``` + +## Quickstart + +Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents. + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "Qwen/Qwen2.5-Coder-7B-Instruct" + +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype="auto", + device_map="auto" +) +tokenizer = AutoTokenizer.from_pretrained(model_name) + +prompt = "write a quick sort algorithm." +messages = [ + {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."}, + {"role": "user", "content": prompt} +] +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True +) +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +generated_ids = model.generate( + **model_inputs, + max_new_tokens=512 +) +generated_ids = [ + output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) +] + +response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] +``` + +### Processing Long Texts + +The current `config.json` is set for context length up to 32,768 tokens. +To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts. + +For supported frameworks, you could add the following to `config.json` to enable YaRN: +```json +{ + ..., + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "type": "yarn" + } +} +``` \ No newline at end of file