commit 9c18048c488b6ed5848861f167424ffdcc50ad89 Author: ModelHub XC Date: Thu Jul 30 10:03:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/R3-Qwen3-4B-14k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7d930d4 --- /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-Qwen3-4B-14k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-14k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/R3-Qwen3-4B-14k.IQ4_XS.gguf b/R3-Qwen3-4B-14k.IQ4_XS.gguf new file mode 100644 index 0000000..9d8610c --- /dev/null +++ b/R3-Qwen3-4B-14k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba1e63b1175a1a3190eaaa7509301900373956a2caf554988df469445c102d49 +size 2286316864 diff --git a/R3-Qwen3-4B-14k.Q2_K.gguf b/R3-Qwen3-4B-14k.Q2_K.gguf new file mode 100644 index 0000000..d12c2ee --- /dev/null +++ b/R3-Qwen3-4B-14k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d4b554de7ae80c8658eb9d2821cc93faa126074f35d516f9d48c794ac851933 +size 1669500224 diff --git a/R3-Qwen3-4B-14k.Q3_K_L.gguf b/R3-Qwen3-4B-14k.Q3_K_L.gguf new file mode 100644 index 0000000..c208ad1 --- /dev/null +++ b/R3-Qwen3-4B-14k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32e23eb7d20f34ec7b971d6d50885d282a211ec7fbd034bfbf8ca2cbad6c388 +size 2239786304 diff --git a/R3-Qwen3-4B-14k.Q3_K_M.gguf b/R3-Qwen3-4B-14k.Q3_K_M.gguf new file mode 100644 index 0000000..415766e --- /dev/null +++ b/R3-Qwen3-4B-14k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0153fb5374b8ce31b3afc66edf52debad4ed8baa8de015a302036a9968e55265 +size 2075618624 diff --git a/R3-Qwen3-4B-14k.Q3_K_S.gguf b/R3-Qwen3-4B-14k.Q3_K_S.gguf new file mode 100644 index 0000000..9f58eb9 --- /dev/null +++ b/R3-Qwen3-4B-14k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0827bbce2a1e21637555e01f02402010c627ca90310faa9576b6ffb76bdbad8 +size 1886997824 diff --git a/R3-Qwen3-4B-14k.Q4_K_M.gguf b/R3-Qwen3-4B-14k.Q4_K_M.gguf new file mode 100644 index 0000000..88cc0c4 --- /dev/null +++ b/R3-Qwen3-4B-14k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba460b9f3975d8ee43327c628ce7a1f2e003b9b59a2f6795d221cb304957266a +size 2497281344 diff --git a/R3-Qwen3-4B-14k.Q4_K_S.gguf b/R3-Qwen3-4B-14k.Q4_K_S.gguf new file mode 100644 index 0000000..479302d --- /dev/null +++ b/R3-Qwen3-4B-14k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125ffcee922455a54531ebd625723a899eae3b53a959d10234d551ef3ccd7c58 +size 2383310144 diff --git a/R3-Qwen3-4B-14k.Q5_K_M.gguf b/R3-Qwen3-4B-14k.Q5_K_M.gguf new file mode 100644 index 0000000..901392a --- /dev/null +++ b/R3-Qwen3-4B-14k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3587594eff1e7cf8bfcc03799ab88fe77b9951becf586c4599f08c5b24c5566 +size 2889514304 diff --git a/R3-Qwen3-4B-14k.Q5_K_S.gguf b/R3-Qwen3-4B-14k.Q5_K_S.gguf new file mode 100644 index 0000000..d88953d --- /dev/null +++ b/R3-Qwen3-4B-14k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0197e5acd3ab37653f7420e62c421d92d2c7150de45472d14c2c11f5107ea9 +size 2823712064 diff --git a/R3-Qwen3-4B-14k.Q6_K.gguf b/R3-Qwen3-4B-14k.Q6_K.gguf new file mode 100644 index 0000000..af63f3d --- /dev/null +++ b/R3-Qwen3-4B-14k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b808fa409b18c22e906d16f86f3b9de418e9236921d76be93354fb1034131ab9 +size 3306261824 diff --git a/R3-Qwen3-4B-14k.Q8_0.gguf b/R3-Qwen3-4B-14k.Q8_0.gguf new file mode 100644 index 0000000..abaf39e --- /dev/null +++ b/R3-Qwen3-4B-14k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a14f3cd6eea060e0cbe80d481839b6ec87cb6a9774324186dbd1c5ff190a7b2 +size 4280405824 diff --git a/R3-Qwen3-4B-14k.f16.gguf b/R3-Qwen3-4B-14k.f16.gguf new file mode 100644 index 0000000..c789978 --- /dev/null +++ b/R3-Qwen3-4B-14k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a293aebf31f13a38f0dc5ee61dd1f2e274fd8c6f66fcc6a3af5cc3bc63ed2257 +size 8051285824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a93977d --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: rubricreward/R3-Qwen3-4B-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-Qwen3-4B-14k + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/R3-Qwen3-4B-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-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-14k-GGUF/resolve/main/R3-Qwen3-4B-14k.f16.gguf) | f16 | 8.2 | 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. + +