commit f867b5814bb8fde9b859805427e5a50ebce47f6c Author: ModelHub XC Date: Mon Aug 10 16:31:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GPT-2-wikitext-chunks-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4bf1000 --- /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 +GPT-2-wikitext-chunks.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GPT-2-wikitext-chunks.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GPT-2-wikitext-chunks.IQ4_XS.gguf b/GPT-2-wikitext-chunks.IQ4_XS.gguf new file mode 100644 index 0000000..ca8cbc6 --- /dev/null +++ b/GPT-2-wikitext-chunks.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9eb7981e80d664cddc20ba376cb4b80a9f1709a1bfd165062a4c6adc6df0a45 +size 82559296 diff --git a/GPT-2-wikitext-chunks.Q2_K.gguf b/GPT-2-wikitext-chunks.Q2_K.gguf new file mode 100644 index 0000000..e6836a6 --- /dev/null +++ b/GPT-2-wikitext-chunks.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda83b6a0a2342fa809a262d45224f7de8ccebf6e1fd64e43743733db2b8a0cd +size 70689088 diff --git a/GPT-2-wikitext-chunks.Q3_K_L.gguf b/GPT-2-wikitext-chunks.Q3_K_L.gguf new file mode 100644 index 0000000..e824177 --- /dev/null +++ b/GPT-2-wikitext-chunks.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a75dee544312399155d7bc8690cd8024bc79bb6e278f769b607e2c45a15436f +size 88162624 diff --git a/GPT-2-wikitext-chunks.Q3_K_M.gguf b/GPT-2-wikitext-chunks.Q3_K_M.gguf new file mode 100644 index 0000000..2069b14 --- /dev/null +++ b/GPT-2-wikitext-chunks.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09da908be02bf83a2c6624124fbe0aaaf7173dc5480ec8296363a01e0cb44ff3 +size 81527104 diff --git a/GPT-2-wikitext-chunks.Q3_K_S.gguf b/GPT-2-wikitext-chunks.Q3_K_S.gguf new file mode 100644 index 0000000..4b20d7e --- /dev/null +++ b/GPT-2-wikitext-chunks.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ecc0e8b6d7f8c39657a7ea4405a5960e964203a2578fe2e46360c1cd539568b +size 73564480 diff --git a/GPT-2-wikitext-chunks.Q4_K_M.gguf b/GPT-2-wikitext-chunks.Q4_K_M.gguf new file mode 100644 index 0000000..75fcd78 --- /dev/null +++ b/GPT-2-wikitext-chunks.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f76a970f4ea7e305273ff6208e1d83e01f8df98468dd7521b440b7a8941f8082 +size 91231552 diff --git a/GPT-2-wikitext-chunks.Q4_K_S.gguf b/GPT-2-wikitext-chunks.Q4_K_S.gguf new file mode 100644 index 0000000..2b1ead4 --- /dev/null +++ b/GPT-2-wikitext-chunks.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dba46962155646ea23f218a2115b26fa35f3e78676b94a55dcf5276d03701db +size 86024512 diff --git a/GPT-2-wikitext-chunks.Q5_K_M.gguf b/GPT-2-wikitext-chunks.Q5_K_M.gguf new file mode 100644 index 0000000..ef0800e --- /dev/null +++ b/GPT-2-wikitext-chunks.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4348848d27bd3bb1842e41e56a8ac1de9d1d15ed6f4c6f63671e96cfd767a48 +size 98751808 diff --git a/GPT-2-wikitext-chunks.Q5_K_S.gguf b/GPT-2-wikitext-chunks.Q5_K_S.gguf new file mode 100644 index 0000000..1db9015 --- /dev/null +++ b/GPT-2-wikitext-chunks.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92cf27ceb6b3d7cda9416e7c980924edef021d2699665a8ca902762530f910c +size 95461696 diff --git a/GPT-2-wikitext-chunks.Q6_K.gguf b/GPT-2-wikitext-chunks.Q6_K.gguf new file mode 100644 index 0000000..8e9c2ba --- /dev/null +++ b/GPT-2-wikitext-chunks.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:527fb6077d2b8723b1add0ae512dd5e982f9110b19c727e6dcdd2fdb06e107f6 +size 106742080 diff --git a/GPT-2-wikitext-chunks.Q8_0.gguf b/GPT-2-wikitext-chunks.Q8_0.gguf new file mode 100644 index 0000000..8547bca --- /dev/null +++ b/GPT-2-wikitext-chunks.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5b745fe28fc299250d49f25e700295c441ee8c2a8c97f65a9074ef68c03e446 +size 136660000 diff --git a/GPT-2-wikitext-chunks.f16.gguf b/GPT-2-wikitext-chunks.f16.gguf new file mode 100644 index 0000000..239458f --- /dev/null +++ b/GPT-2-wikitext-chunks.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc79df6ac418064d4e5b2b6fc2749ad9c63ddcf96db6b58bf6c7de3648b8e91 +size 252471264 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4bb6731 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: EleutherAI/GPT-2-wikitext-chunks +datasets: +- EleutherAI/bergson-wikitext-512-chunks +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/EleutherAI/GPT-2-wikitext-chunks + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GPT-2-wikitext-chunks-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/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GPT-2-wikitext-chunks-GGUF/resolve/main/GPT-2-wikitext-chunks.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. + +