commit 9c9537623d880e04d2dfc4a937c6a72a678646a8 Author: ModelHub XC Date: Sun May 10 07:48:33 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/R3-Qwen3-8B-14k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fa49604 --- /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 +R3-Qwen3-8B-14k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.f16.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-14k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/R3-Qwen3-8B-14k.IQ4_XS.gguf b/R3-Qwen3-8B-14k.IQ4_XS.gguf new file mode 100644 index 0000000..37312a6 --- /dev/null +++ b/R3-Qwen3-8B-14k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42a0ed412cb8a56958402201efc3c5c4a364e0b364a41ab90638d9012c078456 +size 4593297280 diff --git a/R3-Qwen3-8B-14k.Q2_K.gguf b/R3-Qwen3-8B-14k.Q2_K.gguf new file mode 100644 index 0000000..1820b31 --- /dev/null +++ b/R3-Qwen3-8B-14k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa4a3bf74dd892f87c8ef46b003565ba739408c5a1ef76a015eae28cbf69c4e +size 3281733504 diff --git a/R3-Qwen3-8B-14k.Q3_K_L.gguf b/R3-Qwen3-8B-14k.Q3_K_L.gguf new file mode 100644 index 0000000..05ebee4 --- /dev/null +++ b/R3-Qwen3-8B-14k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60529f26ee67a4d1990f8fe110ae6729af8d17696d60aec18e4129540914243e +size 4431394688 diff --git a/R3-Qwen3-8B-14k.Q3_K_M.gguf b/R3-Qwen3-8B-14k.Q3_K_M.gguf new file mode 100644 index 0000000..d3a1f6c --- /dev/null +++ b/R3-Qwen3-8B-14k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4004d3d1823d88e2bbcf413016deb34a94a0ad75044f8708a73dc5d5d09c1846 +size 4124161920 diff --git a/R3-Qwen3-8B-14k.Q3_K_S.gguf b/R3-Qwen3-8B-14k.Q3_K_S.gguf new file mode 100644 index 0000000..de3b9cc --- /dev/null +++ b/R3-Qwen3-8B-14k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:368ef2094e7f17ceb6f8120817599f4b6095e803bb88b8fe96c969883a243288 +size 3769612160 diff --git a/R3-Qwen3-8B-14k.Q4_K_M.gguf b/R3-Qwen3-8B-14k.Q4_K_M.gguf new file mode 100644 index 0000000..e0c1738 --- /dev/null +++ b/R3-Qwen3-8B-14k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a0de51d6fa1a1ca163f63cba58f5adecbfba248b3567e344ca3a89bca31b8c +size 5027784576 diff --git a/R3-Qwen3-8B-14k.Q4_K_S.gguf b/R3-Qwen3-8B-14k.Q4_K_S.gguf new file mode 100644 index 0000000..e1f06a4 --- /dev/null +++ b/R3-Qwen3-8B-14k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea8f4c2cc3561a4e0725dc05fde27316fd05fbe9f1b20eedce3d95b0e37057b +size 4802013056 diff --git a/R3-Qwen3-8B-14k.Q5_K_M.gguf b/R3-Qwen3-8B-14k.Q5_K_M.gguf new file mode 100644 index 0000000..499afdd --- /dev/null +++ b/R3-Qwen3-8B-14k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04799d927594601b85d79216fefe226521363a2a41bc04505c3bc75c93ead99 +size 5851113344 diff --git a/R3-Qwen3-8B-14k.Q5_K_S.gguf b/R3-Qwen3-8B-14k.Q5_K_S.gguf new file mode 100644 index 0000000..0d56f1c --- /dev/null +++ b/R3-Qwen3-8B-14k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d9583db835bc3dbeacfb2f8353502dc5913f72cf08de8bafd55b1385c9683f +size 5720762240 diff --git a/R3-Qwen3-8B-14k.Q6_K.gguf b/R3-Qwen3-8B-14k.Q6_K.gguf new file mode 100644 index 0000000..653833b --- /dev/null +++ b/R3-Qwen3-8B-14k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45c48127bc5288da52b7b7b55939d82ab6dd53e1a8f11d974f3f93a723dd3f9f +size 6725900160 diff --git a/R3-Qwen3-8B-14k.Q8_0.gguf b/R3-Qwen3-8B-14k.Q8_0.gguf new file mode 100644 index 0000000..161463a --- /dev/null +++ b/R3-Qwen3-8B-14k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:724b504cedc6000fafdf454446d14ec652e40c54a7d1825752fcae479175aee4 +size 8709519232 diff --git a/R3-Qwen3-8B-14k.f16.gguf b/R3-Qwen3-8B-14k.f16.gguf new file mode 100644 index 0000000..db6fd18 --- /dev/null +++ b/R3-Qwen3-8B-14k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43fe9c23f8615082975d84344ded2ebb777aaee7c53ad0e51c3e0bea97df586a +size 16388044672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..041d9a0 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: rubricreward/R3-Qwen3-8B-14k +datasets: +- rubricreward/R3-Dataset-14K +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/rubricreward/R3-Qwen3-8B-14k + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-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/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-14k-GGUF/resolve/main/R3-Qwen3-8B-14k.f16.gguf) | f16 | 16.5 | 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. + +