From c0d535bfbcaca2054de8da5231c02d94f1edab9b Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 7 May 2026 23:04:06 +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: prithivMLmods/OpenReasoning-Nemotron-1.5B-F32-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++++++++ OpenReasoning-Nemotron-1.5B.BF16.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.F16.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.F32.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q2_K.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q3_K_L.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q3_K_M.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q3_K_S.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q4_K_M.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q4_K_S.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q5_K_M.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q5_K_S.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q6_K.gguf | 3 ++ OpenReasoning-Nemotron-1.5B.Q8_0.gguf | 3 ++ README.md | 45 +++++++++++++++++++++++ config.json | 3 ++ configuration.json | 1 + 17 files changed, 135 insertions(+) create mode 100644 .gitattributes create mode 100644 OpenReasoning-Nemotron-1.5B.BF16.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.F16.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.F32.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q2_K.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q3_K_L.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q3_K_M.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q3_K_S.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q4_K_M.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q4_K_S.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q5_K_M.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q5_K_S.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q6_K.gguf create mode 100644 OpenReasoning-Nemotron-1.5B.Q8_0.gguf create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/OpenReasoning-Nemotron-1.5B.BF16.gguf b/OpenReasoning-Nemotron-1.5B.BF16.gguf new file mode 100644 index 0000000..2957fda --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f85dede8743e4e3a0bf07ec334681dd1545a7918d77826ee9ad11bbba3c986 +size 3093666784 diff --git a/OpenReasoning-Nemotron-1.5B.F16.gguf b/OpenReasoning-Nemotron-1.5B.F16.gguf new file mode 100644 index 0000000..a5b0d1e --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62e3dd3f5ad35a34a748d6f0bc58c84d7dd2a57d4b0111b4447187624621a30 +size 3093666784 diff --git a/OpenReasoning-Nemotron-1.5B.F32.gguf b/OpenReasoning-Nemotron-1.5B.F32.gguf new file mode 100644 index 0000000..1ee99bc --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f5ffd22b3132f0cdc479456a70e78b7892b1e539b03e0f219c7adeb0638005 +size 6180805600 diff --git a/OpenReasoning-Nemotron-1.5B.Q2_K.gguf b/OpenReasoning-Nemotron-1.5B.Q2_K.gguf new file mode 100644 index 0000000..bfca516 --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:325757983d0c588bda1195463a2113d056dac1c86cc486f27c45610a75563f84 +size 676302304 diff --git a/OpenReasoning-Nemotron-1.5B.Q3_K_L.gguf b/OpenReasoning-Nemotron-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..4fc438b --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a862eb62f6f0307b6335d00505b3f72f613311b3cd12272631a8db904dbc53a +size 880160224 diff --git a/OpenReasoning-Nemotron-1.5B.Q3_K_M.gguf b/OpenReasoning-Nemotron-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..9321160 --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7a28b0b2133bdec0d3803e6a93b2f520adb59d4278588706963d16cf779f2a +size 824176096 diff --git a/OpenReasoning-Nemotron-1.5B.Q3_K_S.gguf b/OpenReasoning-Nemotron-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..45111e2 --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a53d0dff5682d163071e4a983bd08a292d6e2cb5e91b9c8e15c63dd0dc6f78 +size 760942048 diff --git a/OpenReasoning-Nemotron-1.5B.Q4_K_M.gguf b/OpenReasoning-Nemotron-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..babf7a9 --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:464f8cbec869c739e9b06e06d26c9b07a18b1ca985545825fa3aef3854007ea6 +size 986045920 diff --git a/OpenReasoning-Nemotron-1.5B.Q4_K_S.gguf b/OpenReasoning-Nemotron-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..df7c5fe --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:febabe18b16024296f604456470bedc472983de4049c077d48b9862b30a9b3a5 +size 940309984 diff --git a/OpenReasoning-Nemotron-1.5B.Q5_K_M.gguf b/OpenReasoning-Nemotron-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..658a669 --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd452deeeb06a62be603695e07225ccecf2d472431cbb07475def8e9b6b6325 +size 1125047776 diff --git a/OpenReasoning-Nemotron-1.5B.Q5_K_S.gguf b/OpenReasoning-Nemotron-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..871e974 --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5354579bea1a9617407a06f5eeb0dd07185f899bf9c666fc9e376bc970531ffb +size 1098726880 diff --git a/OpenReasoning-Nemotron-1.5B.Q6_K.gguf b/OpenReasoning-Nemotron-1.5B.Q6_K.gguf new file mode 100644 index 0000000..e95cee5 --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c065d6573fd819af5989ec889591869843e94ad289c5e8ed48cd0d89d546739 +size 1272737248 diff --git a/OpenReasoning-Nemotron-1.5B.Q8_0.gguf b/OpenReasoning-Nemotron-1.5B.Q8_0.gguf new file mode 100644 index 0000000..df4aad3 --- /dev/null +++ b/OpenReasoning-Nemotron-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec2083691c415c0799c88073b6e2bd0be712d0c986aedc852940912bb88a8af +size 1646570464 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c9f3aca --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +license: cc-by-4.0 +language: +- en +base_model: +- nvidia/OpenReasoning-Nemotron-1.5B +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +- math +- code +- nvidia +--- + +# **OpenReasoning-Nemotron-1.5B-F32-GGUF** + +> OpenReasoning-Nemotron-1.5B is a large language model (LLM) which is a derivative of Qwen2.5-1.5B-Instruct (AKA the reference model). It is a reasoning model that is post-trained for reasoning about math, code and science solution generation. We evaluated this model with up to 64K output tokens. OpenReasoning-Nemotron models can be used in a "heavy" mode by starting multiple parallel generations and combining them together via generative solution selection (GenSelect). To add this "skill" we follow the original GenSelect training pipeline except we do not train on the selection summary but use the full reasoning trace of DeepSeek R1 0528 671B instead. We only train models to select the best solution for math problems but surprisingly find that this capability directly generalizes to code and science questions! With this "heavy" GenSelect inference mode, OpenReasoning-Nemotron-32B model surpasses O3 (High) on math and coding benchmarks. + +## Model File + +| Quant Type | File Size | Filename | +|------------|-----------|----------| +| F32 | 6.18 GB | OpenReasoning-Nemotron-1.5B.F32.gguf | +| F16 | 3.09 GB | OpenReasoning-Nemotron-1.5B.F16.gguf | +| BF16 | 3.09 GB | OpenReasoning-Nemotron-1.5B.BF16.gguf | +| Q8_0 | 1.65 GB | OpenReasoning-Nemotron-1.5B.Q8_0.gguf | +| Q6_K | 1.27 GB | OpenReasoning-Nemotron-1.5B.Q6_K.gguf | +| Q5_K_M | 1.13 GB | OpenReasoning-Nemotron-1.5B.Q5_K_M.gguf | +| Q5_K_S | 1.1 GB | OpenReasoning-Nemotron-1.5B.Q5_K_S.gguf | +| Q4_K_M | 986 MB | OpenReasoning-Nemotron-1.5B.Q4_K_M.gguf | +| Q4_K_S | 940 MB | OpenReasoning-Nemotron-1.5B.Q4_K_S.gguf | +| Q3_K_L | 880 MB | OpenReasoning-Nemotron-1.5B.Q3_K_L.gguf | +| Q3_K_M | 824 MB | OpenReasoning-Nemotron-1.5B.Q3_K_M.gguf | +| Q3_K_S | 761 MB | OpenReasoning-Nemotron-1.5B.Q3_K_S.gguf | +| Q2_K | 676 MB | OpenReasoning-Nemotron-1.5B.Q2_K.gguf | + +## Quants Usage + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +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) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..5ca493c --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "qwen2" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file