commit 19151267d49b5cfb5872eb7265dabef79adfef7b Author: ModelHub XC Date: Sat Jun 13 18:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fc6c4f6 --- /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 +AutoRefine-Qwen2.5-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AutoRefine-Qwen2.5-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AutoRefine-Qwen2.5-3B-Instruct.IQ4_XS.gguf b/AutoRefine-Qwen2.5-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..2431231 --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3fc334343a01739074955fef67d4ff60863edce1410772897133547bf7a95d +size 1918491520 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q2_K.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..2a4deaf --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5ca1b81733f775924489aca0ee37145622f6f63c7c86b9e2068dc4ea0f6bc8 +size 1376856960 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_L.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..2aa3266 --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c319334fd1c1e76a220b7b4acb524abebb0cb8add271046d2bfee81e66d6c43 +size 1841095552 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_M.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..3400a6d --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3f12cae386a06e98f525a74d4ef2469a9a38d9f8ea5e9ac5bff545710925be +size 1724179328 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_S.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..a69caf7 --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337e66cdfcaa7d575d0915229526d00b0d013eda718e69c501d85ee0d359ef7a +size 1588061056 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q4_K_M.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..7fb2156 --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e13e62e417c4981747f63f9109a39ebc454480e7bdc1e0ac10330dcafb7855 +size 2104933248 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q4_K_S.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..9b70863 --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d47910de7820b0598cbddc18de0d559bbae63ff4f19e4f39aa8611323acb4ef +size 2009414528 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q5_K_M.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..99edad1 --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea0dffed67083a875de222a87861709a4166f706ce1afeeb1ca59372b326eaa +size 2438740864 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q5_K_S.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..76cf91e --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81a56a4ae75cc8e1dbef864e6ee8ddfe156a34802e0ec315974cf17b9db84181 +size 2383592320 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q6_K.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..55de7c2 --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd312ab9d2c3e82bc36a707a96f1339f1704dcf6f7e9dcb814759f4206c5ffc4 +size 2793411456 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.Q8_0.gguf b/AutoRefine-Qwen2.5-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..0ff4add --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef15fcaae52e579344e04cf326640bc5aeceff5f0cb0e625a0cc249f9a9cb8ba +size 3616088960 diff --git a/AutoRefine-Qwen2.5-3B-Instruct.f16.gguf b/AutoRefine-Qwen2.5-3B-Instruct.f16.gguf new file mode 100644 index 0000000..40cb886 --- /dev/null +++ b/AutoRefine-Qwen2.5-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fefc4a2664e6372640ad50d37dacef3e5088ad9bba35615765ebf014aba35c4 +size 6800647040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b1a4b73 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: yrshi/AutoRefine-Qwen2.5-3B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/yrshi/AutoRefine-Qwen2.5-3B-Instruct + + +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/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AutoRefine-Qwen2.5-3B-Instruct-GGUF/resolve/main/AutoRefine-Qwen2.5-3B-Instruct.f16.gguf) | f16 | 6.9 | 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. + +