commit 8546b59bb2cc2a2b3e71df0a63795e4206188e36 Author: ModelHub XC Date: Wed Jul 22 21:01:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8ab400e --- /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-Ja-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.IQ4_XS.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..5e3fa2a --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b5f9bd00e2c53a35322afeb545be0787360da6d237211b51c43e3d78c430ba0 +size 1753185440 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q2_K.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q2_K.gguf new file mode 100644 index 0000000..a50968d --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c82fc889edbb36ffa5214deedb90736ef6fd8cc9eea47081e45117118aa4e7 +size 1274756256 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_L.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..98482ed --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a6aa5ef478b2c1ee2ee5e4cc30f4f6664d407ae9d1b65b0cb71d6030b06020 +size 1707392160 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_M.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..a9c95e5 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b21787d5eb6fdfc3afba7f7dd82a27253c90a425729f75f97cd43b7e6ea9c6b3 +size 1590475936 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_S.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..bdcfa9a --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba95309905d90639cdae2f44c2585bdc7be3128075eb6bc5757b999680f083ca +size 1454357664 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q4_0_4_4.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q4_0_4_4.gguf new file mode 100644 index 0000000..c319596 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c4701bb1f9bb3219a950c19c4aa67951eef211c8e5f089487b25eee992ebec +size 1822850208 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_M.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..ae8cde0 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf9166749f2823215f898b26f5b6cbd7024486fd2d20706910dc56920b5106a +size 1929903264 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_S.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..fb164e2 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7a416d6e0a417688c3a7caff0fedb99e63d5748fbcf30c35c34d2b2811adeb +size 1834384544 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_M.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..e128f4f --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63a2996973d7ec4517aacb4a6b51365bc22e1995fe0aa6ffbbc910ce5faa3934 +size 2224815264 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_S.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..9cca64b --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d3ead77d1a935051cb51d13bedf1813110d6c95e2c23465fc587016127a61a +size 2169666720 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q6_K.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q6_K.gguf new file mode 100644 index 0000000..6a86f4f --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b297f9b2d0c006519dcfa510059fa9e84f40e8331fca7701cf75dd4950022b92 +size 2538159264 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.Q8_0.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.Q8_0.gguf new file mode 100644 index 0000000..a46a884 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:886dd4d28eafe01ad1b7a23bfda7d9d43b3002c1efc8a88d56c366abd4187455 +size 3285476512 diff --git a/Qwen2.5-3B-Instruct-Ja-SFT.f16.gguf b/Qwen2.5-3B-Instruct-Ja-SFT.f16.gguf new file mode 100644 index 0000000..18cb710 --- /dev/null +++ b/Qwen2.5-3B-Instruct-Ja-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04633f1e4b6c01c427032537ef809f53d5e98b89e9404c8803a88d90e6ecbce +size 6178317472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f7338a8 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: jaeyong2/Qwen2.5-3B-Instruct-Ja-SFT +language: +- ja +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/jaeyong2/Qwen2.5-3B-Instruct-Ja-SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-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-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-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-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-SFT.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-Ja-SFT-GGUF/resolve/main/Qwen2.5-3B-Instruct-Ja-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. + +