commit 9779ed44cfd648c12e8cea618cf5669f4ed0da3a Author: ModelHub XC Date: Mon May 25 19:11:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FinNemotron-R1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..96c4132 --- /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 +FinNemotron-R1.f16.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FinNemotron-R1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FinNemotron-R1.IQ4_XS.gguf b/FinNemotron-R1.IQ4_XS.gguf new file mode 100644 index 0000000..2e4885c --- /dev/null +++ b/FinNemotron-R1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f74c2db9aa71a0fe87bbc9d5ac587abe341c2a93ccb92d84f6f158882416343e +size 4250298624 diff --git a/FinNemotron-R1.Q2_K.gguf b/FinNemotron-R1.Q2_K.gguf new file mode 100644 index 0000000..eaa8667 --- /dev/null +++ b/FinNemotron-R1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ccf6dc0c36e9c8bd4f4d0895cea655d978f7053947e6f8742b254a720947ac +size 3015940352 diff --git a/FinNemotron-R1.Q3_K_L.gguf b/FinNemotron-R1.Q3_K_L.gguf new file mode 100644 index 0000000..64268b6 --- /dev/null +++ b/FinNemotron-R1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2ee5e9099b2dde55b407da6132f6706d874676882ce0b1f1cadb5bbb3938f8 +size 4088459520 diff --git a/FinNemotron-R1.Q3_K_M.gguf b/FinNemotron-R1.Q3_K_M.gguf new file mode 100644 index 0000000..c099f1a --- /dev/null +++ b/FinNemotron-R1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdd6eaa189add04190b956c6e6ebf65727e9e018726afc5e11960ddc212f5079 +size 3808391424 diff --git a/FinNemotron-R1.Q3_K_S.gguf b/FinNemotron-R1.Q3_K_S.gguf new file mode 100644 index 0000000..9b4252b --- /dev/null +++ b/FinNemotron-R1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581734e8df016e5406b1c8363431be1e197326217705eb3ef4cc4c836bc06540 +size 3492368640 diff --git a/FinNemotron-R1.Q4_K_M.gguf b/FinNemotron-R1.Q4_K_M.gguf new file mode 100644 index 0000000..71aadc0 --- /dev/null +++ b/FinNemotron-R1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2be944285c0b597b6db3a31402fbdfd92a24c7b7a29942fc245c72d919896e +size 4683073792 diff --git a/FinNemotron-R1.Q4_K_S.gguf b/FinNemotron-R1.Q4_K_S.gguf new file mode 100644 index 0000000..663e022 --- /dev/null +++ b/FinNemotron-R1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2320947cb41a7272ac3f22c227bc01da746fa90fe638887f4d2a820fcf7be5b +size 4457769216 diff --git a/FinNemotron-R1.Q5_K_M.gguf b/FinNemotron-R1.Q5_K_M.gguf new file mode 100644 index 0000000..75beda0 --- /dev/null +++ b/FinNemotron-R1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d845e3cb6ca432bceea4ad19f6ac0317e8242138e7f0fea116b4ead6af4d9c +size 5444831488 diff --git a/FinNemotron-R1.Q5_K_S.gguf b/FinNemotron-R1.Q5_K_S.gguf new file mode 100644 index 0000000..abd6273 --- /dev/null +++ b/FinNemotron-R1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0237a9333ef07c51620faaf9479768d645b8e4a91827ef7653b88debdd4da994 +size 5315176704 diff --git a/FinNemotron-R1.Q6_K.gguf b/FinNemotron-R1.Q6_K.gguf new file mode 100644 index 0000000..8394372 --- /dev/null +++ b/FinNemotron-R1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d22db1bd1d782c2da0d694b95d427cef9fd93c96676bc03eea28c32074c826 +size 6254199040 diff --git a/FinNemotron-R1.Q8_0.gguf b/FinNemotron-R1.Q8_0.gguf new file mode 100644 index 0000000..ea69592 --- /dev/null +++ b/FinNemotron-R1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7110e86475c9b2654eadccabc3290508c8010ac148dde943f60c1e0b82f474 +size 8098525440 diff --git a/FinNemotron-R1.f16.gguf b/FinNemotron-R1.f16.gguf new file mode 100644 index 0000000..66cd0e2 --- /dev/null +++ b/FinNemotron-R1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ba59d4578c0e8542168556af6b3aaa15d1e15ae305ad2bb9ee7bc30e617780 +size 15237853440 diff --git a/README.md b/README.md new file mode 100644 index 0000000..79caa4a --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: wuxianchao/FinNemotron-R1 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/wuxianchao/FinNemotron-R1 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FinNemotron-R1-GGUF/resolve/main/FinNemotron-R1.f16.gguf) | f16 | 15.3 | 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. + +