commit da393bf86085d5dfe77ae27c95dd85d977cdf94c Author: ModelHub XC Date: Mon Oct 19 12:48:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/zelensky-gpt2-125m-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..932b26a --- /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 +zelensky-gpt2-125m.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +zelensky-gpt2-125m.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..529545b --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: slava-medvedev/zelensky-gpt2-125m +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/slava-medvedev/zelensky-gpt2-125m + + +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/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/zelensky-gpt2-125m-GGUF/resolve/main/zelensky-gpt2-125m.f16.gguf) | f16 | 0.4 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/zelensky-gpt2-125m.IQ4_XS.gguf b/zelensky-gpt2-125m.IQ4_XS.gguf new file mode 100644 index 0000000..b9f2759 --- /dev/null +++ b/zelensky-gpt2-125m.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:926564d73a227bbfd138bc7abe92f76671cbcc083a089755b75ceb97744560bb +size 103064256 diff --git a/zelensky-gpt2-125m.Q2_K.gguf b/zelensky-gpt2-125m.Q2_K.gguf new file mode 100644 index 0000000..ef6307a --- /dev/null +++ b/zelensky-gpt2-125m.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77360032c76b2332f248d756b047c7334cb40a31bb2fa9f0e520b9b3f99a985d +size 81197408 diff --git a/zelensky-gpt2-125m.Q3_K_L.gguf b/zelensky-gpt2-125m.Q3_K_L.gguf new file mode 100644 index 0000000..bf9bed9 --- /dev/null +++ b/zelensky-gpt2-125m.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8001bd69c2800a5cdbb74de9ced968d57ef624494f8db5ce06391e0b9f8bc32 +size 102093344 diff --git a/zelensky-gpt2-125m.Q3_K_M.gguf b/zelensky-gpt2-125m.Q3_K_M.gguf new file mode 100644 index 0000000..3572b2f --- /dev/null +++ b/zelensky-gpt2-125m.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edbbb990ead144d90a3efebeb3c0f3528d21f69a19bbad16d0402f6553df8696 +size 97669664 diff --git a/zelensky-gpt2-125m.Q3_K_S.gguf b/zelensky-gpt2-125m.Q3_K_S.gguf new file mode 100644 index 0000000..a41e7d0 --- /dev/null +++ b/zelensky-gpt2-125m.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c461e626ab09e30ad31076dfde434fa8aa669c3003e04dad72b1358df02e2b2c +size 90149408 diff --git a/zelensky-gpt2-125m.Q4_K_M.gguf b/zelensky-gpt2-125m.Q4_K_M.gguf new file mode 100644 index 0000000..fd99410 --- /dev/null +++ b/zelensky-gpt2-125m.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d0d84b9672b37389b8954798df0fefd135d1295f4c6abe51496fea96a577094 +size 112859744 diff --git a/zelensky-gpt2-125m.Q4_K_S.gguf b/zelensky-gpt2-125m.Q4_K_S.gguf new file mode 100644 index 0000000..a1f8d2f --- /dev/null +++ b/zelensky-gpt2-125m.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebcbdbd31d2fb2731ebd89382c2559cd8c2e2e1ed0dd10b7c38d4ea33ebce66d +size 106850912 diff --git a/zelensky-gpt2-125m.Q5_K_M.gguf b/zelensky-gpt2-125m.Q5_K_M.gguf new file mode 100644 index 0000000..42ce969 --- /dev/null +++ b/zelensky-gpt2-125m.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b7c132bf5e757535e177f5c02695633b142c9fb2b99eae814c8847a74311d2c +size 126697664 diff --git a/zelensky-gpt2-125m.Q5_K_S.gguf b/zelensky-gpt2-125m.Q5_K_S.gguf new file mode 100644 index 0000000..f553004 --- /dev/null +++ b/zelensky-gpt2-125m.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b61bb8dda26ca3694e1542b6a2a26ba1cc277f9c53b4e6938348576ec54bdde +size 121997504 diff --git a/zelensky-gpt2-125m.Q6_K.gguf b/zelensky-gpt2-125m.Q6_K.gguf new file mode 100644 index 0000000..1b6a3d8 --- /dev/null +++ b/zelensky-gpt2-125m.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bf1d14a0c426f23b0c3f95571b1ab57360dc1f02df32dbc1792cdcfa159c605 +size 138404096 diff --git a/zelensky-gpt2-125m.Q8_0.gguf b/zelensky-gpt2-125m.Q8_0.gguf new file mode 100644 index 0000000..beaa7d2 --- /dev/null +++ b/zelensky-gpt2-125m.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:381c4e4dce50160ec89758448dceeec48071df2f704bee078addffedd57bd74d +size 177669824 diff --git a/zelensky-gpt2-125m.f16.gguf b/zelensky-gpt2-125m.f16.gguf new file mode 100644 index 0000000..0926183 --- /dev/null +++ b/zelensky-gpt2-125m.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:985d5e91b6721a90ad66db18f0b93d362d162d0773a469fbd44d53d87f85a0ae +size 329666112