commit 2978a1aabc90b6e4d07871b7f3008693d9fc2e16 Author: ModelHub XC Date: Thu Apr 23 20:33:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..46e498c --- /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-LoRA-4k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +R3-Qwen3-4B-LoRA-4k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/R3-Qwen3-4B-LoRA-4k.IQ4_XS.gguf b/R3-Qwen3-4B-LoRA-4k.IQ4_XS.gguf new file mode 100644 index 0000000..0823771 --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33bd8b3b4057bd2cda1a84a70685a8d93b1f04d06679cfb44a7215edde4eca8c +size 2286316224 diff --git a/R3-Qwen3-4B-LoRA-4k.Q2_K.gguf b/R3-Qwen3-4B-LoRA-4k.Q2_K.gguf new file mode 100644 index 0000000..2484288 --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e06439d3823d66dad307ef8b8b148c2927ed5f0e76162d7edb099b1aa9ab50 +size 1669499584 diff --git a/R3-Qwen3-4B-LoRA-4k.Q3_K_L.gguf b/R3-Qwen3-4B-LoRA-4k.Q3_K_L.gguf new file mode 100644 index 0000000..9915a09 --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d00d72b2228320317604cec27d7e9af0d49ae64489f5ce1d5c78da8fef37043 +size 2239785664 diff --git a/R3-Qwen3-4B-LoRA-4k.Q3_K_M.gguf b/R3-Qwen3-4B-LoRA-4k.Q3_K_M.gguf new file mode 100644 index 0000000..ce3e93d --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24893110d2df527203bb45f9a9393dcef407cd32a3919558f013bdd178448376 +size 2075617984 diff --git a/R3-Qwen3-4B-LoRA-4k.Q3_K_S.gguf b/R3-Qwen3-4B-LoRA-4k.Q3_K_S.gguf new file mode 100644 index 0000000..e875140 --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:525ba3ab7f506d669c82a56aabeccaefd99213f955552458ead9072199ee5ce2 +size 1886997184 diff --git a/R3-Qwen3-4B-LoRA-4k.Q4_K_M.gguf b/R3-Qwen3-4B-LoRA-4k.Q4_K_M.gguf new file mode 100644 index 0000000..661a4e9 --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e5fbcf714466e9ffc5e6e5dd6f5e60bcf9c04327f0f9582b74592eb1818e949 +size 2497280704 diff --git a/R3-Qwen3-4B-LoRA-4k.Q4_K_S.gguf b/R3-Qwen3-4B-LoRA-4k.Q4_K_S.gguf new file mode 100644 index 0000000..e53280b --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f9cb7870bf6409aeb1d26efc5f6bfe52f0d50f7676c482c444dd0b631b7b292 +size 2383309504 diff --git a/R3-Qwen3-4B-LoRA-4k.Q5_K_M.gguf b/R3-Qwen3-4B-LoRA-4k.Q5_K_M.gguf new file mode 100644 index 0000000..1c0fb55 --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99ab3e1f6f942bef7d60ea020e5479c50bb1a22d9cbd448c75549037e81ca770 +size 2889513664 diff --git a/R3-Qwen3-4B-LoRA-4k.Q5_K_S.gguf b/R3-Qwen3-4B-LoRA-4k.Q5_K_S.gguf new file mode 100644 index 0000000..b18d360 --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41899e3d6a428744ac015ae752ff4e0b71adc4a14ca61e138a69ac85a3abb676 +size 2823711424 diff --git a/R3-Qwen3-4B-LoRA-4k.Q6_K.gguf b/R3-Qwen3-4B-LoRA-4k.Q6_K.gguf new file mode 100644 index 0000000..309bbac --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b031f70aa000955add57c14b0effb0bbfd7f837c1202437ad7a415c064c277a +size 3306261184 diff --git a/R3-Qwen3-4B-LoRA-4k.Q8_0.gguf b/R3-Qwen3-4B-LoRA-4k.Q8_0.gguf new file mode 100644 index 0000000..f5af91f --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d75c958c5ea730fd90115850c1ee9015176f498f0436cd6d9af79452be2a4d4d +size 4280405184 diff --git a/R3-Qwen3-4B-LoRA-4k.f16.gguf b/R3-Qwen3-4B-LoRA-4k.f16.gguf new file mode 100644 index 0000000..ae8a666 --- /dev/null +++ b/R3-Qwen3-4B-LoRA-4k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf0e11c356028ae5933eb77958ead569f4e3b369dd23b2b35d387b73e5750a5a +size 8051285184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fed7c4d --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: rubricreward/R3-Qwen3-4B-LoRA-4k +datasets: +- rubricreward/R3-Dataset-4K +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- lora +--- +## About + + + + + + +static quants of https://huggingface.co/rubricreward/R3-Qwen3-4B-LoRA-4k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#R3-Qwen3-4B-LoRA-4k-GGUF).*** + +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/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-4B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-4B-LoRA-4k.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. + +