commit 205320f4c881472f85d9f9ed3d16c63891dd3937 Author: ModelHub XC Date: Sat May 9 10:47:51 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/R3-Qwen3-8B-4k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a269c55 --- /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-4k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.f16.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-8B-4k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/R3-Qwen3-8B-4k.IQ4_XS.gguf b/R3-Qwen3-8B-4k.IQ4_XS.gguf new file mode 100644 index 0000000..288d248 --- /dev/null +++ b/R3-Qwen3-8B-4k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdeab84f969609b7354fa82829361daf61047b8e5c2bda34128c7495afe198b +size 4593297248 diff --git a/R3-Qwen3-8B-4k.Q2_K.gguf b/R3-Qwen3-8B-4k.Q2_K.gguf new file mode 100644 index 0000000..8fe0960 --- /dev/null +++ b/R3-Qwen3-8B-4k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dddfd5491dfe4d8f421c9fd071150124b888a34a345c830792bafbac259a1660 +size 3281733472 diff --git a/R3-Qwen3-8B-4k.Q3_K_L.gguf b/R3-Qwen3-8B-4k.Q3_K_L.gguf new file mode 100644 index 0000000..907b5f6 --- /dev/null +++ b/R3-Qwen3-8B-4k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a3e63bc44fff9d7c39942cb22a86533d8d390770a4686a94cb50302489200e +size 4431394656 diff --git a/R3-Qwen3-8B-4k.Q3_K_M.gguf b/R3-Qwen3-8B-4k.Q3_K_M.gguf new file mode 100644 index 0000000..d2e49e2 --- /dev/null +++ b/R3-Qwen3-8B-4k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9801b564120b105d4a612b3610784b5ca934579fb7db818abce3744742dfa3f6 +size 4124161888 diff --git a/R3-Qwen3-8B-4k.Q3_K_S.gguf b/R3-Qwen3-8B-4k.Q3_K_S.gguf new file mode 100644 index 0000000..69733ef --- /dev/null +++ b/R3-Qwen3-8B-4k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b2392c7d2f4c8a4f8cff0da45da431aa990caadf83ba644f7026cf6a85c83bb +size 3769612128 diff --git a/R3-Qwen3-8B-4k.Q4_K_M.gguf b/R3-Qwen3-8B-4k.Q4_K_M.gguf new file mode 100644 index 0000000..21fddc3 --- /dev/null +++ b/R3-Qwen3-8B-4k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e87a5b0ba2c9f08dcb62d75d2dc5ae60e6f82222c386c6a1542c717d06313df +size 5027784544 diff --git a/R3-Qwen3-8B-4k.Q4_K_S.gguf b/R3-Qwen3-8B-4k.Q4_K_S.gguf new file mode 100644 index 0000000..743a7a3 --- /dev/null +++ b/R3-Qwen3-8B-4k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3849c2f9354864f70fe13f5b4e99658a75ea2b863e12633146a597c56b18a2df +size 4802013024 diff --git a/R3-Qwen3-8B-4k.Q5_K_M.gguf b/R3-Qwen3-8B-4k.Q5_K_M.gguf new file mode 100644 index 0000000..89a0730 --- /dev/null +++ b/R3-Qwen3-8B-4k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ef4507511f4770ae1accbc06c6a39676a836294f6cb745faca9ea87a38c826 +size 5851113312 diff --git a/R3-Qwen3-8B-4k.Q5_K_S.gguf b/R3-Qwen3-8B-4k.Q5_K_S.gguf new file mode 100644 index 0000000..62f3a0a --- /dev/null +++ b/R3-Qwen3-8B-4k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7205dfe69df22737141d18074d268fd547851133f19c441b71410946bc05198e +size 5720762208 diff --git a/R3-Qwen3-8B-4k.Q6_K.gguf b/R3-Qwen3-8B-4k.Q6_K.gguf new file mode 100644 index 0000000..5afec7f --- /dev/null +++ b/R3-Qwen3-8B-4k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f955008f04d0b0b32f395dc3c0994a0929c229318e202ff26d6016392d55655 +size 6725900128 diff --git a/R3-Qwen3-8B-4k.Q8_0.gguf b/R3-Qwen3-8B-4k.Q8_0.gguf new file mode 100644 index 0000000..ad11f15 --- /dev/null +++ b/R3-Qwen3-8B-4k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0df8973b04e6187ab33bf3ea25067d327ef9b9114427e1ba08c8d317b8edaccc +size 8709519200 diff --git a/R3-Qwen3-8B-4k.f16.gguf b/R3-Qwen3-8B-4k.f16.gguf new file mode 100644 index 0000000..0c88c96 --- /dev/null +++ b/R3-Qwen3-8B-4k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add168a9bdea886822a65a1f47b1d78ffa6db9a5c4e82536c65c8e25824b1d00 +size 16388044640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..31ae41d --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: rubricreward/R3-Qwen3-8B-4k +datasets: +- rubricreward/R3-Dataset-4K +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/rubricreward/R3-Qwen3-8B-4k + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-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-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-4k-GGUF/resolve/main/R3-Qwen3-8B-4k.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. + +