commit 24e89598b07849720d4c8bf3520960cbe4679750 Author: ModelHub XC Date: Mon Aug 10 13:47:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..61b4f4d --- /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 +*.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 +Nemotron-Research-Reasoning-Qwen-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron-Research-Reasoning-Qwen-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.IQ4_XS.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..abca635 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50309a81ab8e5f4991d661cd5dda5e68884d8ed07bf2e215a2424a09d5eb5bcc +size 1026162880 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q2_K.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q2_K.gguf new file mode 100644 index 0000000..0c1fea9 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f4738bb7118fa65893b063d0fbdea56d0320d13b6d33a51917a6de4b389effc +size 752880832 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_L.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..f28980b --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65ef5548895b4bddaf021fbad35561c37700d9b3af6840638dc003e74593ce51 +size 980440768 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_M.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..a5aed34 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aad091c5d114124493ee1665f8891085eeffc9b38e9ea221b52f8ff5b9ca9d9 +size 924456640 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_S.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..70c62d7 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20018c074db63910c2afec445d605b2cf9944d1094eb3d74c454a181d0a7cf9c +size 861222592 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_M.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..69a3989 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe943535a50cfb407da6ad633421fded007472792231e0044cb5f6ac38f60450 +size 1117321408 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_S.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..29340d3 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eff81ac67ea477a0947b8b0029ef18ef07cd34e08b4f875dbb6d8a6e78af4a6 +size 1071585472 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_M.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..269c828 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebb9c589bcd39ff5269ab221e2f7b5b8bf8baebc2b7ccf42a3caf0ca406b0543 +size 1285494976 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_S.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..a6e0afc --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c129c9e1f8c31222a7af160712af228d816d061a47c6d7b3261bb344a4dab49 +size 1259174080 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q6_K.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q6_K.gguf new file mode 100644 index 0000000..0536bb0 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4126079933279b66ef4d6907dc3630d688160a1ea3197938a3324be7a0e1d957 +size 1464179392 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.Q8_0.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.Q8_0.gguf new file mode 100644 index 0000000..ec04637 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13b13be6096a5f44c3b15e8bb20008b5a4a3d98b981662fd5d706ed579e5ee3c +size 1894532800 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.f16.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.f16.gguf new file mode 100644 index 0000000..0e6815b --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba578e68a701ace38f76dda6ef4945f32749675bd8566f5528a5f7599c999667 +size 3560416960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ff94ba0 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: nvidia/Nemotron-Research-Reasoning-Qwen-1.5B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/nvidia/Nemotron-Research-Reasoning-Qwen-1.5B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-i1-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/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-GGUF/resolve/main/Nemotron-Research-Reasoning-Qwen-1.5B.f16.gguf) | f16 | 3.7 | 16 bpw, overkill | + +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. + +