commit 484778f7ad5519c57530825e304e9a2b790a879e Author: ModelHub XC Date: Thu Oct 15 20:52:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Research-Reasoning-Qwen-F32-GGUF Source: Original Platform 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/Nemotron-Research-Reasoning-Qwen-1.5B.BF16.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.BF16.gguf new file mode 100644 index 0000000..c0140f2 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54571e8f93260f3c15cef1ba181cebdd4634941f53462237e01402fd480dfa7b +size 3560415968 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..33589c9 --- /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:a16c592ed2d4e8a640adbef15832323ef15e24a4dec6697c2e6fdc474eaae4e4 +size 3560415968 diff --git a/Nemotron-Research-Reasoning-Qwen-1.5B.F32.gguf b/Nemotron-Research-Reasoning-Qwen-1.5B.F32.gguf new file mode 100644 index 0000000..8572d74 --- /dev/null +++ b/Nemotron-Research-Reasoning-Qwen-1.5B.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc60f4e621f9f6d92bec60da7a45698cb72680f8b8a0a7534d451c080a31f9bf +size 7114302176 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..1eec070 --- /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 sha256:1eba9989e371d0885e01037b88aab8ba39d2186051a613a74b2bd9ca48be1f8c +size 752879840 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..c4f8b1d --- /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 sha256:4e762ef0b78366011d2a1e59fd68b85eb1ea620d12288282d45fafd4bfc3fc1a +size 980439776 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..aa71889 --- /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 sha256:6e937e0c648aa21ee1654fd7b2b5405a86cf9807abd236bfdc45b8836dd51419 +size 924455648 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..c00efde --- /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:d70ae6e5110e6f441fbeb716ffa0c31deebc4db782f06a3a1789a136529e8e06 +size 861221600 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..518154a --- /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:ab32600410cf9b88442536e90314f06ddffa444ff6c4e04d22c64c6230485515 +size 1117320416 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..2932791 --- /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:a6dbc31911e5b7932b94644da8f0f3b8e1eb3816fca54709cfe08b8545771474 +size 1071584480 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..a152f3f --- /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 sha256:2a5aaac743abf6479f72177a62ab1defbd6448a39ad6068a44db593ec4d91f3a +size 1285493984 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..1b3bcaf --- /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 sha256:1d1e2209096d1b3d75c2f6965d5eca5bc2dc64835afdf56f855c6782471950ed +size 1259173088 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..7db2a5d --- /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:a894d4ce6a5334d1ab0557d92000f0b4fbcb8af34ed1bd87645b0adc7b0b8f9e +size 1894531808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8163b60 --- /dev/null +++ b/README.md @@ -0,0 +1,51 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- nvidia/Nemotron-Research-Reasoning-Qwen-1.5B +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +- code +- reasoning +- research +--- + +# **Nemotron-Research-Reasoning-Qwen-1.5B-GGUF** + +> [Nemotron-Research-Reasoning-Qwen-1.5B](https://huggingface.co/nvidia/Nemotron-Research-Reasoning-Qwen-1.5B) is the world’s leading 1.5B open-weight model for complex reasoning tasks such as mathematical problems, coding challenges, scientific questions, and logic puzzles. It is trained using the ProRL algorithm on a diverse and comprehensive set of datasets. Our model has achieved impressive results, outperforming Deepseek’s 1.5B model by a large margin on a broad range of tasks, including math, coding, and GPQA. + +## Model Files + +| File Name | Format | Size | Precision | Use Case | +|-----------|--------|------|-----------|----------| +| `Nemotron-Research-Reasoning-Qwen-1.5B.F32.gguf` | GGUF | 7.11 GB | F32 | Highest precision, research use | +| `Nemotron-Research-Reasoning-Qwen-1.5B.BF16.gguf` | GGUF | 3.56 GB | BF16 | High precision, balanced performance | +| `Nemotron-Research-Reasoning-Qwen-1.5B.F16.gguf` | GGUF | 3.56 GB | F16 | High precision, memory efficient | +| `Nemotron-Research-Reasoning-Qwen-1.5B.Q8_0.gguf` | GGUF | 1.89 GB | Q8_0 | Good quality, moderate compression | +| `Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_M.gguf` | GGUF | 1.29 GB | Q5_K_M | Balanced quality/size (recommended) | +| `Nemotron-Research-Reasoning-Qwen-1.5B.Q5_K_S.gguf` | GGUF | 1.26 GB | Q5_K_S | Good quality, smaller size | +| `Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_M.gguf` | GGUF | 1.12 GB | Q4_K_M | Good balance for most users | +| `Nemotron-Research-Reasoning-Qwen-1.5B.Q4_K_S.gguf` | GGUF | 1.07 GB | Q4_K_S | Decent quality, compact size | +| `Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_L.gguf` | GGUF | 980 MB | Q3_K_L | Lower quality, very compact | +| `Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_M.gguf` | GGUF | 924 MB | Q3_K_M | Fast inference, limited quality | +| `Nemotron-Research-Reasoning-Qwen-1.5B.Q3_K_S.gguf` | GGUF | 861 MB | Q3_K_S | Fastest inference, basic quality | +| `Nemotron-Research-Reasoning-Qwen-1.5B.Q2_K.gguf` | GGUF | 753 MB | Q2_K | Minimal size, experimental use | + +### Quick Selection Guide + +- **For Research/Development**: Use `F32` or `BF16` for maximum accuracy +- **For Production (Recommended)**: Use `Q5_K_M` for best quality/performance balance +- **For Resource-Constrained Environments**: Use `Q4_K_M` or `Q4_K_S` +- **For Edge Devices**: Use `Q3_K_M` or `Q2_K` for minimal footprint + +## 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..abb5987 --- /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