commit c8d73c02966d65190dceb4bf463e282da32c19cc Author: ModelHub XC Date: Fri Jul 17 08:07:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-2B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3edc5a8 --- /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 +Qwen2.5-2B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-2B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-2B-Instruct.IQ4_XS.gguf b/Qwen2.5-2B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..edb9f3e --- /dev/null +++ b/Qwen2.5-2B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c04f8b8012efa7b7f4ea8feaf9c9a0bfb10b7f8f2854540fc7075e12abd7865 +size 1631209440 diff --git a/Qwen2.5-2B-Instruct.Q2_K.gguf b/Qwen2.5-2B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..e00ad39 --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:916db48b6513974efb87025fb1eda43371a523ff46727ac38e4b4a420ea15cc3 +size 1163396064 diff --git a/Qwen2.5-2B-Instruct.Q3_K_L.gguf b/Qwen2.5-2B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..f53f818 --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8dc9c4349e6075b01abb70225289743215402fb1abed22594aa9f31c954758a +size 1565691360 diff --git a/Qwen2.5-2B-Instruct.Q3_K_M.gguf b/Qwen2.5-2B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..25c6454 --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b497f7a168fc2daac83b1624e5f14283ce28ee673eb87656b857353557fc02d4 +size 1463602656 diff --git a/Qwen2.5-2B-Instruct.Q3_K_S.gguf b/Qwen2.5-2B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..295a519 --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5915ec8f7abfb785a4dcf4e398671f4533b57dcaf7760b38d240491e0ec36b6 +size 1344286176 diff --git a/Qwen2.5-2B-Instruct.Q4_K_M.gguf b/Qwen2.5-2B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..69a92e5 --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d995f2079570de41396765b6f6f8a92a180e0f772d22ba9c4889ee45de51c1d9 +size 1793331168 diff --git a/Qwen2.5-2B-Instruct.Q4_K_S.gguf b/Qwen2.5-2B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..9c9a4fb --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59958a1cf3908089857e42a352298ab71599389e600901986329af60fdae0b88 +size 1708961760 diff --git a/Qwen2.5-2B-Instruct.Q5_K_M.gguf b/Qwen2.5-2B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..4d7084a --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdab2ee100a3144d94816348733f6a38cc8fdd7a8e909e8b5a8831f6b15264a9 +size 2080649184 diff --git a/Qwen2.5-2B-Instruct.Q5_K_S.gguf b/Qwen2.5-2B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..8693784 --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9f2ad49e5e55e8c81cb1e0dcc2ff11cc58f26631282ca08573f64baae92363c +size 2031767520 diff --git a/Qwen2.5-2B-Instruct.Q6_K.gguf b/Qwen2.5-2B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..d7d1f19 --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc8fa1cd6d29d3ad018977adf4ffe169c89edbc008e812821f391278a84d9741 +size 2385924576 diff --git a/Qwen2.5-2B-Instruct.Q8_0.gguf b/Qwen2.5-2B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..b19aa5a --- /dev/null +++ b/Qwen2.5-2B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc920140724dee11e7130696b8ad812f81d6647a72f64bf6e16e33da2623e5f2 +size 3088260576 diff --git a/Qwen2.5-2B-Instruct.f16.gguf b/Qwen2.5-2B-Instruct.f16.gguf new file mode 100644 index 0000000..e4599b2 --- /dev/null +++ b/Qwen2.5-2B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad64eba62df0f31af80f26b381420946af0b15cde28bf5c453f15106253643a +size 5806980576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d42083d --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: win10/Qwen2.5-2B-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- Qwen/Qwen2.5-1.5B-Instruct +--- +## About + + + + + + +static quants of https://huggingface.co/win10/Qwen2.5-2B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-2B-Instruct-GGUF).*** + +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/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q6_K.gguf) | Q6_K | 2.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.Q8_0.gguf) | Q8_0 | 3.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-2B-Instruct-GGUF/resolve/main/Qwen2.5-2B-Instruct.f16.gguf) | f16 | 5.9 | 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. + +