From 99b3a88f3bfd431069718211880d9522dde329ed Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 19 Sep 2026 05:12:16 +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: gabriellarson/OpenCodeReasoning-Nemotron-1.1-7B-GGUF Source: Original Platform --- .gitattributes | 61 ++++++ OpenCodeReasoning-Nemotron-1.1-7B-F16.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ1_M.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ1_S.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ2_M.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ2_S.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XS.gguf | 3 + ...CodeReasoning-Nemotron-1.1-7B-IQ2_XXS.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ3_M.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ3_S.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XS.gguf | 3 + ...CodeReasoning-Nemotron-1.1-7B-IQ3_XXS.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ4_NL.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-IQ4_XS.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q2_K.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q2_K_S.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_L.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_M.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_S.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q4_0.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_M.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_S.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q5_0.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_M.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_S.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q6_K.gguf | 3 + OpenCodeReasoning-Nemotron-1.1-7B-Q8_0.gguf | 3 + README.md | 196 ++++++++++++++++++ 28 files changed, 335 insertions(+) create mode 100644 .gitattributes create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-F16.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ1_M.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ1_S.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ2_M.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ2_S.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XS.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XXS.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ3_M.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ3_S.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XS.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XXS.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ4_NL.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-IQ4_XS.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q2_K.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q2_K_S.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_L.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_M.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_S.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q4_0.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_M.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_S.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q5_0.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_M.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_S.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q6_K.gguf create mode 100644 OpenCodeReasoning-Nemotron-1.1-7B-Q8_0.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f39a95a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,61 @@ +*.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 +OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenCodeReasoning-Nemotron-1.1-7B-F16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-F16.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-F16.gguf new file mode 100644 index 0000000..d00cf07 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a54b544ddeb68eeb1d0f755da0a2e5408c59bdb0d189d96a5209e6983f072906 +size 15237853760 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ1_M.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ1_M.gguf new file mode 100644 index 0000000..a313973 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:052ee4f669032e6c8f1ae791bfcf2582490c068de6a022c1675ec25fcf496601 +size 2042196832 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ1_S.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ1_S.gguf new file mode 100644 index 0000000..06b648f --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aeef91be1712f9d5e37b3a5ae0ce8ebe6f346bfc4cfda064739cd81204e29bd +size 1903668064 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_M.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_M.gguf new file mode 100644 index 0000000..6b8d34c --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9e3884837db9e3b8e9a2fd09d61c39376bff60f02ad17ccb0aa69128ffbdc8 +size 2780343136 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_S.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_S.gguf new file mode 100644 index 0000000..cb87d5e --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df45f6f683b33eaa65a0b4bb4d9e87386811ae65d4ddc4b0636f998d31cf670 +size 2595638112 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XS.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XS.gguf new file mode 100644 index 0000000..604b2b8 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2d3e9913ad99ac5df7255c9788c829261d02138b9e5d1bb3c669ef71b875b1a +size 2469022560 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XXS.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XXS.gguf new file mode 100644 index 0000000..cda77b9 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b52a6870324658eaa6f81f879b1b099f4ffb708dc0af107452b543ad01aae4f3 +size 2273078112 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_M.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_M.gguf new file mode 100644 index 0000000..86e281e --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2564b9b965136a46e766fd000f8b49ddb18602912cf177e20d6f53af08c27b14 +size 3574012768 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_S.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_S.gguf new file mode 100644 index 0000000..bbe8120 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d28e287479971bbe3ae67a966381f774b97d4b8e3bbd15a9e6b762cfeff1fef +size 3499193184 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XS.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XS.gguf new file mode 100644 index 0000000..8b67e0d --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5e6afaf0226bf520d739d77a7a6e74c44572a23873273e155a72a5a2e188d53 +size 3346256736 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XXS.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XXS.gguf new file mode 100644 index 0000000..76850c5 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f66082c3ca3cbaa94228390309eec2475eb3d9727de5a98693724b18dce7a4 +size 3114515296 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ4_NL.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ4_NL.gguf new file mode 100644 index 0000000..85fa5a4 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05b889420c842616ceae6f5110935d88ac632954c2d9118df52a3bd2a1f3349b +size 4437814112 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-IQ4_XS.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-IQ4_XS.gguf new file mode 100644 index 0000000..9071132 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daaa4712a192812306b6034b51de7dc88e12c878e2241665fdda40da4d2da04a +size 4218473312 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q2_K.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q2_K.gguf new file mode 100644 index 0000000..709cef8 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:743b483af27a45a329adbbc204e98eae4abc8923a717e5a610f371353f55820c +size 3015940960 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q2_K_S.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q2_K_S.gguf new file mode 100644 index 0000000..93a8ba4 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6087935d5fce17719f9942fcee88535be3cd22a6ba8ef44f2ecf3226ca5f5ec +size 2834074464 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_L.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_L.gguf new file mode 100644 index 0000000..18fa204 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2529fa5fa29fd495347ff500bae9f1d700bbdf47952616b70a058884f3dd0873 +size 4088460128 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_M.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_M.gguf new file mode 100644 index 0000000..3c39976 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb90942ea85a5908324dc956df72c7ae306511ff129b85dfa4d8f30be7e6e1d +size 3808392032 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_S.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_S.gguf new file mode 100644 index 0000000..428fca0 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdebedbc5338784f07dbfd28431d80b85226c0b4801c82a0d8754a516b3142f9 +size 3492369248 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q4_0.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q4_0.gguf new file mode 100644 index 0000000..d8b5438 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd6b60f2496ae1e2afaa8398bccd1386757e9caba32fdc2af87ed82c902343c +size 4444121952 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_M.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_M.gguf new file mode 100644 index 0000000..dbbc4aa --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1f5e23f67a6c27b9c475d362c10ff401621193c6e1054b790edd1197e87859 +size 4683074400 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_S.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_S.gguf new file mode 100644 index 0000000..d0dcddb --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e4de2cafbe359ee0c2eadeda67972431b7ca6e022f760a430ee8fb39fe7e41 +size 4457769824 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q5_0.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q5_0.gguf new file mode 100644 index 0000000..7e56bc5 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbcd49141324167d53576fc9bd3b1da7eae73476285a6162e93f900f1581c4b0 +size 5327907680 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_M.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_M.gguf new file mode 100644 index 0000000..ccc9098 --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0962b671955ad1e6e1cd3145591f81237a291589e68fb915a9e641cc351e288 +size 5444832096 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_S.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_S.gguf new file mode 100644 index 0000000..0ddd1ae --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1487f9d1d1477c76e1b1d1636ebad684cb13ac632a04e4dc46895447ff358d +size 5315177312 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q6_K.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q6_K.gguf new file mode 100644 index 0000000..b2cac5e --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd88248081651ca00efb7fc64cd997cd6063b9027ac96f4dcf2c5feb225e95d +size 6254199648 diff --git a/OpenCodeReasoning-Nemotron-1.1-7B-Q8_0.gguf b/OpenCodeReasoning-Nemotron-1.1-7B-Q8_0.gguf new file mode 100644 index 0000000..5bc107a --- /dev/null +++ b/OpenCodeReasoning-Nemotron-1.1-7B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a5e01af1799fa0058e11ecfd1d1446127a7a8e78c49a18e6293b44f48a5dab +size 8098526048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ab23305 --- /dev/null +++ b/README.md @@ -0,0 +1,196 @@ +--- +base_model: +- nvidia/OpenCodeReasoning-Nemotron-1.1-7B +datasets: +- nvidia/OpenCodeReasoning +language: +- en +library_name: transformers +tags: +- nvidia +- code +pipeline_tag: text-generation +--- +# OpenCodeReasoning-Nemotron-1.1-7B Overview + +## Description:
+OpenCodeReasoning-Nemotron-1.1-7B is a large language model (LLM) which is a derivative of Qwen2.5-7B-Instruct (AKA the reference model). It is a reasoning model that is post-trained for reasoning for code generation. The model supports a context length of 64k tokens.
+ +This model is ready for commercial/non-commercial use.
+ +![Evaluation Results](./results.png) + + +## Results + +Below results are the average of **64 evaluations** on LiveCodeBench (v5) [2408-2501]. + +| Model | Pass@1 | +|:---------------------------------------|:-------------------| +| DeepSeek-R1-0528 | 73.4 | +| DeepSeek-R1 | 65.6 | +| QwQ-32B | 61.3 | +| | | +| **Distilled 7B+ Models** | | +| | | +| Bespoke-Stratos-7B | 14.7 | +| OpenThinker-7B | 25.5 | +| R1-Distill-Qwen-7B | 38.0 | +| OlympicCoder-7B | 40.9 | +| **OpenCodeReasoning-Nemotron-7B** | **51.3** | +| **OpenCodeReasoning-Nemotron-1.1-7B** | **55.5** | +| | | +| **Distilled 14B+ Models** | | +| | | +| R1-Distill-Qwen-14B | 51.3 | +| **OpenCodeReasoning-Nemotron-14B** | **59.4** | +| **OpenCodeReasoning-Nemotron-1.1-14B** | **65.9** | +| | | +| **Distilled 32B+ Models** | | +| | | +| Bespoke-Stratos-32B | 30.1 | +| OpenThinker-32B | 54.1 | +| R1-Distill-Qwen-32B | 58.1 | +| OlympicCoder-32B | 57.4 | +| **OpenCodeReasoning-Nemotron-32B** | **61.7** | +| **OpenCodeReasoning-Nemotron-1.1-32B** | **69.9** | + + +## Reproducing our results + +* [Models](https://huggingface.co/collections/nvidia/opencodereasoning-67ec462892673a326c0696c1) +* [Dataset](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) +* [Paper](https://arxiv.org/abs/2504.01943) + + +## How to use the models? + +To run inference on coding problems: + +````python +import transformers +import torch +model_id = "nvidia/OpenCodeReasoning-Nemotron-7B-v1.1" +pipeline = transformers.pipeline( + "text-generation", + model=model_id, + model_kwargs={"torch_dtype": torch.bfloat16}, + device_map="auto", +) +prompt = """You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below. +Please use python programming language only. +You must use ```python for just the final solution code block with the following format: +```python +# Your code here +``` +{user} +""" +messages = [ + { + "role": "user", + "content": prompt.format(user="Write a program to calculate the sum of the first $N$ fibonacci numbers") + }, +] +outputs = pipeline( + messages, + max_new_tokens=49152, +) +print(outputs[0]["generated_text"][-1]['content']) +```` + + +## Citation + +If you find the data useful, please cite: +``` +@article{ahmad2025opencodereasoning, + title={OpenCodeReasoning: Advancing Data Distillation for Competitive Coding}, + author={Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar, Aleksander Ficek, Siddhartha Jain, Jocelyn Huang, Vahid Noroozi, Boris Ginsburg}, + year={2025}, + eprint={2504.01943}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2504.01943}, +} +``` + +## Additional Information + +## Model Architecture:
+Architecture Type: Dense decoder-only Transformer model +Network Architecture: Qwen-7B-Instruct +
+**This model was developed based on Qwen2.5-7B-Instruct and has 7B model parameters.
** +**OpenCodeReasoning-Nemotron-1.1-7B was developed based on Qwen2.5-7B-Instruct and has 7B model parameters.
** + +## Input:
+**Input Type(s):** Text
+**Input Format(s):** String
+**Input Parameters:** One-Dimensional (1D)
+**Other Properties Related to Input:** Context length up to 65,536 tokens
+ +## Output:
+**Output Type(s):** Text
+**Output Format:** String
+**Output Parameters:** One-Dimensional (1D)
+**Other Properties Related to Output:** Context length up to 65,536 tokens
+ +Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
+ +## Software Integration :
+* Runtime Engine: NeMo 2.3.0
+* Recommended Hardware Microarchitecture Compatibility:
+NVIDIA Ampere
+NVIDIA Hopper
+* Preferred/Supported Operating System(s): Linux
+ +## Model Version(s): +1.1 (07/08/2025)
+OpenCodeReasoning-Nemotron-1.1-7B
+OpenCodeReasoning-Nemotron-1.1-14B
+OpenCodeReasoning-Nemotron-1.1-32B
+ + +# Training and Evaluation Datasets:
+ +## Training Dataset: + +The training corpus for OpenCodeReasoning-Nemotron-1.1-7B is [OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) dataset, which is composed of competitive programming questions and DeepSeek-R1-0528 generated responses. + +Data Collection Method: Hybrid: Automated, Human, Synthetic
+Labeling Method: Hybrid: Automated, Human, Synthetic
+Properties: 1.165M samples from OpenCodeReasoning (https://huggingface.co/datasets/nvidia/OpenCodeReasoning) + +## Evaluation Dataset: +We used the datasets listed in the next section to evaluate OpenCodeReasoning-Nemotron-1.1-7B.
+**Data Collection Method: Hybrid: Automated, Human, Synthetic
** +**Labeling Method: Hybrid: Automated, Human, Synthetic
** + + + +### License/Terms of Use:
+GOVERNING TERMS: Use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Apache License Version 2.0](https://huggingface.co/Qwen/Qwen2.5-32B/blob/main/LICENSE). + +### Deployment Geography: +Global
+ +### Use Case:
+This model is intended for developers and researchers building LLMs.
+ +### Release Date:
+Huggingface [07/08/2025] via https://huggingface.co/nvidia/OpenCodeReasoning-Nemotron-1.1-7B/
+ +## Reference(s): +[2504.01943] OpenCodeReasoning: Advancing Data Distillation for Competitive Coding +
+ +## Inference: +**Engine:** vLLM
+**Test Hardware** NVIDIA H100-80GB
+ +## Ethical Considerations: +NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. + +For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards. + +Please report security vulnerabilities or NVIDIA AI Concerns here. \ No newline at end of file