commit 27d171674018b4db3a030524e2e13a8777277756 Author: ModelHub XC Date: Thu Oct 8 17:59:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PuchifyT2-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2781ed5 --- /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 +PuchifyT2-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PuchifyT2-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PuchifyT2-8B.IQ4_XS.gguf b/PuchifyT2-8B.IQ4_XS.gguf new file mode 100644 index 0000000..6412dfb --- /dev/null +++ b/PuchifyT2-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2e0fe629733236b5b4bf7dab79b46a2ec84207ceec4d6e7aea19c4fabd5e23 +size 4593296832 diff --git a/PuchifyT2-8B.Q2_K.gguf b/PuchifyT2-8B.Q2_K.gguf new file mode 100644 index 0000000..00d0df4 --- /dev/null +++ b/PuchifyT2-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4673fe8d245cc37d0d77d0e368d02c39e16f612d26d841d07dd033be563678a4 +size 3281733056 diff --git a/PuchifyT2-8B.Q3_K_L.gguf b/PuchifyT2-8B.Q3_K_L.gguf new file mode 100644 index 0000000..7fbb23c --- /dev/null +++ b/PuchifyT2-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15192dc2a6a698c5a099f3e9c36477e788e0de85d5fd3b66f38adb234c553003 +size 4431394240 diff --git a/PuchifyT2-8B.Q3_K_M.gguf b/PuchifyT2-8B.Q3_K_M.gguf new file mode 100644 index 0000000..92e9ae9 --- /dev/null +++ b/PuchifyT2-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c73787156e5ff952faffdd51687edd36a6ed3daf5c7b6d66d64b7a5a960378 +size 4124161472 diff --git a/PuchifyT2-8B.Q3_K_S.gguf b/PuchifyT2-8B.Q3_K_S.gguf new file mode 100644 index 0000000..05ec75c --- /dev/null +++ b/PuchifyT2-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5feee6f5498db930d02cd50bdfb9c88525408d89f8ee3386be3d0345da3764 +size 3769611712 diff --git a/PuchifyT2-8B.Q4_K_M.gguf b/PuchifyT2-8B.Q4_K_M.gguf new file mode 100644 index 0000000..610fae6 --- /dev/null +++ b/PuchifyT2-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e9c53d1236604721c56b499e72b0a66b6961aef77fd9a096d3e4c2ffaf9881 +size 5027784128 diff --git a/PuchifyT2-8B.Q4_K_S.gguf b/PuchifyT2-8B.Q4_K_S.gguf new file mode 100644 index 0000000..2e8ec8b --- /dev/null +++ b/PuchifyT2-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcfb37b6b92452bdee98120e14a49c5d102e411ad1c288e13ab08f822a30f486 +size 4802012608 diff --git a/PuchifyT2-8B.Q5_K_M.gguf b/PuchifyT2-8B.Q5_K_M.gguf new file mode 100644 index 0000000..41484fe --- /dev/null +++ b/PuchifyT2-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d0710520c1c654dee3f8f8bae6ff18d23b5cf689beed00c45951fc218c07e28 +size 5851112896 diff --git a/PuchifyT2-8B.Q5_K_S.gguf b/PuchifyT2-8B.Q5_K_S.gguf new file mode 100644 index 0000000..ac4fbfb --- /dev/null +++ b/PuchifyT2-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a154a381f198dcc42d9de754daae763bc0006d6522365f322031617c06192bd +size 5720761792 diff --git a/PuchifyT2-8B.Q6_K.gguf b/PuchifyT2-8B.Q6_K.gguf new file mode 100644 index 0000000..e48eb20 --- /dev/null +++ b/PuchifyT2-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56bfd82783c81cf9108563316d74f684ef0b59d2e36fe9dc4e5e889c84599602 +size 6725899712 diff --git a/PuchifyT2-8B.Q8_0.gguf b/PuchifyT2-8B.Q8_0.gguf new file mode 100644 index 0000000..8825db7 --- /dev/null +++ b/PuchifyT2-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e2595461857e74285ce9efa57d616092dad4a00fed98003ee5d476bbe0492b +size 8709518784 diff --git a/PuchifyT2-8B.f16.gguf b/PuchifyT2-8B.f16.gguf new file mode 100644 index 0000000..478f2ef --- /dev/null +++ b/PuchifyT2-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828e076a22ee002624e78b4f6ddcd75ad426fc2b970b090ecd62461301a7f22b +size 16388044224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..17b9f2a --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Puchify/PuchifyT2-8B +language: +- en +library_name: transformers +license: openrail +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- transformers +- causal-language-model +- S.A.F.E-Framework +- reasoning +- T2-Model-Family +--- +## About + + + + + + +static quants of https://huggingface.co/Puchify/PuchifyT2-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PuchifyT2-8B-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/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PuchifyT2-8B-GGUF/resolve/main/PuchifyT2-8B.f16.gguf) | f16 | 16.5 | 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. + +