commit e9880b16233a12dfa3324fec9bb565ae41362546 Author: ModelHub XC Date: Wed Jun 3 18:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PLLuM-12B-base-2412-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e341bf4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +PLLuM-12B-base-2412.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-base-2412.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PLLuM-12B-base-2412.IQ4_XS.gguf b/PLLuM-12B-base-2412.IQ4_XS.gguf new file mode 100644 index 0000000..b7e7155 --- /dev/null +++ b/PLLuM-12B-base-2412.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9020caa264d78fd8eb8231ca1e0549916e47b4166601629c5df2b49a4d6525cd +size 6800053248 diff --git a/PLLuM-12B-base-2412.Q2_K.gguf b/PLLuM-12B-base-2412.Q2_K.gguf new file mode 100644 index 0000000..6e37c2e --- /dev/null +++ b/PLLuM-12B-base-2412.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9112b00433a122c1122b577a4b7fd52cea74146f8e71acf51863e16912c230b2 +size 4791047168 diff --git a/PLLuM-12B-base-2412.Q3_K_L.gguf b/PLLuM-12B-base-2412.Q3_K_L.gguf new file mode 100644 index 0000000..71f02e3 --- /dev/null +++ b/PLLuM-12B-base-2412.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a94855e1c8ea500b352a334601eff7115f3c928a053fbf52e2944fa5aeef049 +size 6561502208 diff --git a/PLLuM-12B-base-2412.Q3_K_M.gguf b/PLLuM-12B-base-2412.Q3_K_M.gguf new file mode 100644 index 0000000..14f4ee3 --- /dev/null +++ b/PLLuM-12B-base-2412.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:388a1aa16e292714dccdbc7ca44bf1de65517515408336ea76454a4362edd606 +size 6083089408 diff --git a/PLLuM-12B-base-2412.Q3_K_S.gguf b/PLLuM-12B-base-2412.Q3_K_S.gguf new file mode 100644 index 0000000..42f89d8 --- /dev/null +++ b/PLLuM-12B-base-2412.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a645f6461edbaf27fa4cbaa548fcd59bc774fca7acf2ef40e8e3102b565bf3b9 +size 5534225408 diff --git a/PLLuM-12B-base-2412.Q4_K_M.gguf b/PLLuM-12B-base-2412.Q4_K_M.gguf new file mode 100644 index 0000000..da5e5d9 --- /dev/null +++ b/PLLuM-12B-base-2412.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b7d3d9fc6792d8cc4ae4cc9bcb72b296fd77f1eb14f499251b7092a1de7e99 +size 7477203968 diff --git a/PLLuM-12B-base-2412.Q4_K_S.gguf b/PLLuM-12B-base-2412.Q4_K_S.gguf new file mode 100644 index 0000000..5210a95 --- /dev/null +++ b/PLLuM-12B-base-2412.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb4ee3e736d717477c482105e0707bbe34931ce7059cc2ba116d46bd77d2af87 +size 7120196608 diff --git a/PLLuM-12B-base-2412.Q5_K_M.gguf b/PLLuM-12B-base-2412.Q5_K_M.gguf new file mode 100644 index 0000000..dee0d3e --- /dev/null +++ b/PLLuM-12B-base-2412.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5c6ceacd50ce0d73ba0d289ecf2118da294ef37fba9783b1870b2e0adfbb8f +size 8727630848 diff --git a/PLLuM-12B-base-2412.Q5_K_S.gguf b/PLLuM-12B-base-2412.Q5_K_S.gguf new file mode 100644 index 0000000..c67c3f1 --- /dev/null +++ b/PLLuM-12B-base-2412.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b47d634579a7cfa2265bdafdb7530bd618ab0d9c833fa390e88a9f392cf034 +size 8518734848 diff --git a/PLLuM-12B-base-2412.Q6_K.gguf b/PLLuM-12B-base-2412.Q6_K.gguf new file mode 100644 index 0000000..162f82f --- /dev/null +++ b/PLLuM-12B-base-2412.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10375bb51d39d320b7367bd791f5007b8f72faa9c15fb34ce945fd711f20dcc5 +size 10056209408 diff --git a/PLLuM-12B-base-2412.Q8_0.gguf b/PLLuM-12B-base-2412.Q8_0.gguf new file mode 100644 index 0000000..eb38da7 --- /dev/null +++ b/PLLuM-12B-base-2412.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3878e9cf0991ed0e651bce7c77ad837c06035d80032d48ac898ad5be4d5b04 +size 13022368768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6e3a7db --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: CYFRAGOVPL/PLLuM-12B-base-2412 +language: +- pl +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/CYFRAGOVPL/PLLuM-12B-base-2412 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PLLuM-12B-base-2412-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/PLLuM-12B-base-2412-i1-GGUF +## 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/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q3_K_S.gguf) | Q3_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q3_K_L.gguf) | Q3_K_L | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.IQ4_XS.gguf) | IQ4_XS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q5_K_S.gguf) | Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q5_K_M.gguf) | Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q6_K.gguf) | Q6_K | 10.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-base-2412-GGUF/resolve/main/PLLuM-12B-base-2412.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality | + +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. + +