commit aa1b0036806cf5f4029d5628b7185a7e9692391a Author: ModelHub XC Date: Tue Jun 2 01:32:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..85b20d2 --- /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 +Orion-Qwen3-4B-SFT-v2605.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Orion-Qwen3-4B-SFT-v2605.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Orion-Qwen3-4B-SFT-v2605.IQ4_XS.gguf b/Orion-Qwen3-4B-SFT-v2605.IQ4_XS.gguf new file mode 100644 index 0000000..8a042f5 --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bb54a3b5f78f7c877ed6092a2aa24e5bf3ca8228f0a7b60531c1c7116fa9794 +size 2286316736 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q2_K.gguf b/Orion-Qwen3-4B-SFT-v2605.Q2_K.gguf new file mode 100644 index 0000000..f4d2432 --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6db44defd1cb356cd867a2dd3e4bac48d6fa0946476b6e6ffe44470b3b2c70fd +size 1669500096 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q3_K_L.gguf b/Orion-Qwen3-4B-SFT-v2605.Q3_K_L.gguf new file mode 100644 index 0000000..2180b4d --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9608faf22294cf82aebc773d8352730104d6aea1ed863da1c38adc2bdaa77af +size 2239786176 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q3_K_M.gguf b/Orion-Qwen3-4B-SFT-v2605.Q3_K_M.gguf new file mode 100644 index 0000000..3f68ca0 --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a92fa551005656ac639b025143c67b34ed70a3f99f0ff9a9cb24de06db6dec62 +size 2075618496 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q3_K_S.gguf b/Orion-Qwen3-4B-SFT-v2605.Q3_K_S.gguf new file mode 100644 index 0000000..18365b3 --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c8d7da1258af97c491b876755e0723e755e55a8eff6fd7ae85c757bc784fd88 +size 1886997696 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q4_K_M.gguf b/Orion-Qwen3-4B-SFT-v2605.Q4_K_M.gguf new file mode 100644 index 0000000..2d0f383 --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b9e1bfa35c23bc5b099acef7232cfe0809f4a175f1cbc2ab2720d51cf674f12 +size 2497281216 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q4_K_S.gguf b/Orion-Qwen3-4B-SFT-v2605.Q4_K_S.gguf new file mode 100644 index 0000000..b2cb34e --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220f702e8035dbbe49456b8a59d9211aadacc2c080a2ede46c1c732f0f72f3f0 +size 2383310016 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q5_K_M.gguf b/Orion-Qwen3-4B-SFT-v2605.Q5_K_M.gguf new file mode 100644 index 0000000..a8f9749 --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43d17faf6356c213ae846aa1bdd180633ef568634acea4b365025a44a4502a99 +size 2889514176 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q5_K_S.gguf b/Orion-Qwen3-4B-SFT-v2605.Q5_K_S.gguf new file mode 100644 index 0000000..1fd0473 --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a1ed3292a610df2717c27337a81d9e114677d0d57b9ae0d99308c32dbdc7f5 +size 2823711936 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q6_K.gguf b/Orion-Qwen3-4B-SFT-v2605.Q6_K.gguf new file mode 100644 index 0000000..d984895 --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:932a3110eb2ab9848895701fe75effed24b4012c114fad08c1beddf38475012b +size 3306261696 diff --git a/Orion-Qwen3-4B-SFT-v2605.Q8_0.gguf b/Orion-Qwen3-4B-SFT-v2605.Q8_0.gguf new file mode 100644 index 0000000..ff87e5c --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7155e1b1f62a6e6e61adbc66494dd5bcff38592261f5b01fc2775a5504d25727 +size 4280405696 diff --git a/Orion-Qwen3-4B-SFT-v2605.f16.gguf b/Orion-Qwen3-4B-SFT-v2605.f16.gguf new file mode 100644 index 0000000..c3cd5a2 --- /dev/null +++ b/Orion-Qwen3-4B-SFT-v2605.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d18ba804478161336bd73928b5a05ef9d2e87082e40ce9a4578489536fcc38 +size 8051285696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..411bf08 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: 3tic/Orion-Qwen3-4B-SFT-v2605 +language: +- ja +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- lightnovel +--- +## About + + + + + + + + + +static quants of https://huggingface.co/3tic/Orion-Qwen3-4B-SFT-v2605 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Orion-Qwen3-4B-SFT-v2605-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-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/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Orion-Qwen3-4B-SFT-v2605-GGUF/resolve/main/Orion-Qwen3-4B-SFT-v2605.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. + +