commit bd8eca928bdd0093006710c4deb33d72611e8e39 Author: ModelHub XC Date: Wed Jul 22 12:06:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c0a19be --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen2.5-3B-Instruct-Hi-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Hi-SFT.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.IQ4_XS.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..a15ca1d --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3be0de8295b216ed919e3eed953143056012ad6b7a948024456d9f1895150a +size 1753185440 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q2_K.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q2_K.gguf new file mode 100644 index 0000000..47a1236 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d60077cf2ac7a8e3018f612836aa9188465d2a48673e6dda889782a427cda94 +size 1274756256 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_L.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..3421d2c --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01cdb1fbd2d34964da6c7661db0f35c2b55d7b2e4d15af06d0117ad87ebc877a +size 1707392160 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_M.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..38b7d59 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d705f122ebb36c6e6081ff579a67ddba6bd79ddff4c848324fc3429d25cc1d +size 1590475936 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_S.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..18f088b --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ef56b70c4662b0079960c792af0d0d9fb2f5d01a05e812ccf243b41e2fb440 +size 1454357664 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q4_0_4_4.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q4_0_4_4.gguf new file mode 100644 index 0000000..5761f7d --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f808d52576f7c28afe67eeab38b9f3e736f1de2f2793301f271b7db38e7370f +size 1822850208 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_M.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..03f7576 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0423e0025dc5913c114bcc78f8b26f4db01b56bc0e7d6587e953640e44caeff5 +size 1929903264 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_S.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..170198a --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e5dc0b2ab284a98b14e8059f554f32ba75dc625851a5f0030c6c8208ce740d7 +size 1834384544 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_M.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..c3468ee --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a95abeb755428a483316d142f116b20bf08937b5c766eb4d6d0de32a45f1cc1d +size 2224815264 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_S.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..ca90c55 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:240fee38ef81ff5e1b107f3697294705988cdae96693c73818143808b8e1ed3f +size 2169666720 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q6_K.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q6_K.gguf new file mode 100644 index 0000000..6205023 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:319259ad6f26a16370de1e4fee465c35bf0077ab61a8b57f3a2f7baacc8923f7 +size 2538159264 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.Q8_0.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.Q8_0.gguf new file mode 100644 index 0000000..48da11b --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a4c8031b3fd874f5070b8bebed134140d427e2785b7e571feff474eaac32572 +size 3285476512 diff --git a/Qwen2.5-3B-Instruct-Hi-SFT.f16.gguf b/Qwen2.5-3B-Instruct-Hi-SFT.f16.gguf new file mode 100644 index 0000000..c8b0d3a --- /dev/null +++ b/Qwen2.5-3B-Instruct-Hi-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f01bb232f0a9367073d4d24e519c6d7d230c486f97939beadb0e2f04a78879a9 +size 6178317472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ecc8238 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: jaeyong2/Qwen2.5-3B-Instruct-Hi-SFT +language: +- hi +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/jaeyong2/Qwen2.5-3B-Instruct-Hi-SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-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/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Hi-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Hi-SFT.f16.gguf) | f16 | 6.3 | 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. + +