commit 33511e78d3d4a86d4df6c2d388a7f1a5946e073f Author: ModelHub XC Date: Tue Jun 16 00:04:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NOVER1-Qwen3-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2d5b91d --- /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 +NOVER1-Qwen3-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NOVER1-Qwen3-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NOVER1-Qwen3-4B.IQ4_XS.gguf b/NOVER1-Qwen3-4B.IQ4_XS.gguf new file mode 100644 index 0000000..d1e6bdb --- /dev/null +++ b/NOVER1-Qwen3-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:271f911fa9e437954dad83c25bd7b0c210b47e373c10f96451506dfec6500673 +size 2492949920 diff --git a/NOVER1-Qwen3-4B.Q2_K.gguf b/NOVER1-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..f3da0f5 --- /dev/null +++ b/NOVER1-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd89d3fcbc6084f776bbdf0383604a899ac7ce0429078827f7633f250634a2e +size 1797126560 diff --git a/NOVER1-Qwen3-4B.Q3_K_L.gguf b/NOVER1-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..e159bf0 --- /dev/null +++ b/NOVER1-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91822c8cd2e7db6df2c7042b28c695a741e8d0710db3c1cd1307499a9db3d4a2 +size 2406916000 diff --git a/NOVER1-Qwen3-4B.Q3_K_M.gguf b/NOVER1-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..12904ca --- /dev/null +++ b/NOVER1-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623da3f174b5a309758cd3792f81f12122f9f182ddf16433c66c9ffd3fa809d4 +size 2242748320 diff --git a/NOVER1-Qwen3-4B.Q3_K_S.gguf b/NOVER1-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..12ad51d --- /dev/null +++ b/NOVER1-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3886becafdd485b4fc673d776986f90763b61b83e1885f3c97b24a9682542ee +size 2054127520 diff --git a/NOVER1-Qwen3-4B.Q4_K_M.gguf b/NOVER1-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..c3f98d3 --- /dev/null +++ b/NOVER1-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8d43880bf14f8de3c4fc58ab1588824db48166e33ba444c3212606edc5a24f2 +size 2716069280 diff --git a/NOVER1-Qwen3-4B.Q4_K_S.gguf b/NOVER1-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..24fb07d --- /dev/null +++ b/NOVER1-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27602dca206fd5b8b1859b44add9c4fb600b77e1a52ee6eae2b0db6751d1826d +size 2602098080 diff --git a/NOVER1-Qwen3-4B.Q5_K_M.gguf b/NOVER1-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..487f87e --- /dev/null +++ b/NOVER1-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02836f4fe39e5b802e43bec5420bda98b85ca9b3eb75ddf2fa095ea057a0d4ef +size 3156921760 diff --git a/NOVER1-Qwen3-4B.Q5_K_S.gguf b/NOVER1-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..8404852 --- /dev/null +++ b/NOVER1-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34a4c66bb840937a0052a331172c54b74ba3c4fead891e26e235486d23f78ff +size 3091119520 diff --git a/NOVER1-Qwen3-4B.Q6_K.gguf b/NOVER1-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..1994b18 --- /dev/null +++ b/NOVER1-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a30da801dfb7c7355202ea2520c566dc7a1dbe925032c9300fb2aa35a0222b5 +size 3625327520 diff --git a/NOVER1-Qwen3-4B.Q8_0.gguf b/NOVER1-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..ac7dc61 --- /dev/null +++ b/NOVER1-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f67a8127d23947ec58d5e1cd101bd108a0a083c0377d86e0bb5ca6da4610821 +size 4693671840 diff --git a/NOVER1-Qwen3-4B.f16.gguf b/NOVER1-Qwen3-4B.f16.gguf new file mode 100644 index 0000000..3ec6453 --- /dev/null +++ b/NOVER1-Qwen3-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4892ccc3f1897d4dd08fe3c5c85b511d260480b3d622e0c9339baaef7b1b856 +size 8829198240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3fe59c --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: thinkwee/NOVER1-Qwen3-4B +datasets: +- thinkwee/NOVEReason_5k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nover +- reasoning +- rlvr +- lrm +- general_reasoning +- verifier_free +--- +## About + + + + + + + + + +static quants of https://huggingface.co/thinkwee/NOVER1-Qwen3-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NOVER1-Qwen3-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-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/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NOVER1-Qwen3-4B-GGUF/resolve/main/NOVER1-Qwen3-4B.f16.gguf) | f16 | 8.9 | 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. + +