commit 1ab8c984ee3611ed432ba1c1cf12dccd842bade6 Author: ModelHub XC Date: Tue Jun 16 02:18:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CosmoGPT2-Mini-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c3c1497 --- /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 +CosmoGPT2-Mini.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CosmoGPT2-Mini.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CosmoGPT2-Mini.IQ4_XS.gguf b/CosmoGPT2-Mini.IQ4_XS.gguf new file mode 100644 index 0000000..c4d0c2a --- /dev/null +++ b/CosmoGPT2-Mini.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80c638ac7326e8f92ad0425b1f2e683ce2f42b8da861843270556d65da94b8cb +size 82558880 diff --git a/CosmoGPT2-Mini.Q2_K.gguf b/CosmoGPT2-Mini.Q2_K.gguf new file mode 100644 index 0000000..dc499e1 --- /dev/null +++ b/CosmoGPT2-Mini.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64cfb0816bf2114af6ce4ae0ef708f88c324ae5a967ef947e2dfbb3d9e536707 +size 70688672 diff --git a/CosmoGPT2-Mini.Q3_K_L.gguf b/CosmoGPT2-Mini.Q3_K_L.gguf new file mode 100644 index 0000000..10ed557 --- /dev/null +++ b/CosmoGPT2-Mini.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5c31ef22fe566a4a852ac7bf8edfbb335e8a55dec163c63af97913c965aea1 +size 88162208 diff --git a/CosmoGPT2-Mini.Q3_K_M.gguf b/CosmoGPT2-Mini.Q3_K_M.gguf new file mode 100644 index 0000000..4791809 --- /dev/null +++ b/CosmoGPT2-Mini.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f368d307af061d15931ee12eec9accaa886173d05ed737b872a6d73a7352a599 +size 81526688 diff --git a/CosmoGPT2-Mini.Q3_K_S.gguf b/CosmoGPT2-Mini.Q3_K_S.gguf new file mode 100644 index 0000000..27776a3 --- /dev/null +++ b/CosmoGPT2-Mini.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cefe529d5b5fec96388b1ceb7980dd3ef56de084ffd16b4266f72c3cbbfbe5da +size 73564064 diff --git a/CosmoGPT2-Mini.Q4_K_M.gguf b/CosmoGPT2-Mini.Q4_K_M.gguf new file mode 100644 index 0000000..83d99b8 --- /dev/null +++ b/CosmoGPT2-Mini.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6816262b85f6af96cd9cf5bdf15e2944b11cb35aafb88bc7e387a836f60e04cc +size 91231136 diff --git a/CosmoGPT2-Mini.Q4_K_S.gguf b/CosmoGPT2-Mini.Q4_K_S.gguf new file mode 100644 index 0000000..2b59df3 --- /dev/null +++ b/CosmoGPT2-Mini.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8256292d7632dbfe7cee1146bb71e5f54bab342dc20156512904458e1fcbda8 +size 86024096 diff --git a/CosmoGPT2-Mini.Q5_K_M.gguf b/CosmoGPT2-Mini.Q5_K_M.gguf new file mode 100644 index 0000000..4c3df69 --- /dev/null +++ b/CosmoGPT2-Mini.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2860cb3349bc77ff369ef187b92b5716461f9c9a467cb60096eae688f196b77 +size 98751392 diff --git a/CosmoGPT2-Mini.Q5_K_S.gguf b/CosmoGPT2-Mini.Q5_K_S.gguf new file mode 100644 index 0000000..297cf04 --- /dev/null +++ b/CosmoGPT2-Mini.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20c9fe0f57625e57fd6ff96380a7e80b241142712b3389305d3df2ae90ed614a +size 95461280 diff --git a/CosmoGPT2-Mini.Q6_K.gguf b/CosmoGPT2-Mini.Q6_K.gguf new file mode 100644 index 0000000..b3b0790 --- /dev/null +++ b/CosmoGPT2-Mini.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d18da53499a93bc95a566773b43b546852d0bbde3819adc23277f72f8f401f83 +size 106741664 diff --git a/CosmoGPT2-Mini.Q8_0.gguf b/CosmoGPT2-Mini.Q8_0.gguf new file mode 100644 index 0000000..f223d51 --- /dev/null +++ b/CosmoGPT2-Mini.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e639fb2fd3d5eafdcc005988e2e3751d605208ad58a72c2d6380b058118406 +size 136659584 diff --git a/CosmoGPT2-Mini.f16.gguf b/CosmoGPT2-Mini.f16.gguf new file mode 100644 index 0000000..17cc7cf --- /dev/null +++ b/CosmoGPT2-Mini.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c17c9277fdc6ae76d26a5e3056ab24015d73fa94a265f39d08650b97781f27 +size 252470848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d824d07 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: iko-01/CosmoGPT2-Mini +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/iko-01/CosmoGPT2-Mini + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CosmoGPT2-Mini-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/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CosmoGPT2-Mini-GGUF/resolve/main/CosmoGPT2-Mini.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. + +