commit 32bd2138dc8cc04b5217e6cea17e9816722bb41e Author: ModelHub XC Date: Mon Jun 1 03:09:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-PLLuM-8B-base-250801-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..49d6266 --- /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 +Llama-PLLuM-8B-base-250801.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-250801.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-PLLuM-8B-base-250801.IQ4_XS.gguf b/Llama-PLLuM-8B-base-250801.IQ4_XS.gguf new file mode 100644 index 0000000..cb67088 --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20fb214b8b67cc671e41d04da8cefd251e630403623a752da9e88b20ef16d71e +size 4484363360 diff --git a/Llama-PLLuM-8B-base-250801.Q2_K.gguf b/Llama-PLLuM-8B-base-250801.Q2_K.gguf new file mode 100644 index 0000000..c1681b7 --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61b468ce04e9fa81d9bcaa605141f8e094a8f458162dc13897c6be9ad4a1ae5 +size 3179132000 diff --git a/Llama-PLLuM-8B-base-250801.Q3_K_L.gguf b/Llama-PLLuM-8B-base-250801.Q3_K_L.gguf new file mode 100644 index 0000000..afa7775 --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:568c17537fef667dedaa656ee2a7f5aa28a9afdf29669024d6248caa6c449caf +size 4321956960 diff --git a/Llama-PLLuM-8B-base-250801.Q3_K_M.gguf b/Llama-PLLuM-8B-base-250801.Q3_K_M.gguf new file mode 100644 index 0000000..8252074 --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b8590eb5e32807484d2f432a61c37222db707e1d1db44606ed7dbde1382c50 +size 4018918496 diff --git a/Llama-PLLuM-8B-base-250801.Q3_K_S.gguf b/Llama-PLLuM-8B-base-250801.Q3_K_S.gguf new file mode 100644 index 0000000..4a31869 --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2b274cf6c40033c4da233e3ff3356f7caafea617a39edb1fe6a45d46501e08 +size 3664499808 diff --git a/Llama-PLLuM-8B-base-250801.Q4_K_M.gguf b/Llama-PLLuM-8B-base-250801.Q4_K_M.gguf new file mode 100644 index 0000000..401c8f0 --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:149f29c31c45b9ff90090fa63a8d51134e23a26218ab47a2e8f9cc1418a8c755 +size 4920734816 diff --git a/Llama-PLLuM-8B-base-250801.Q4_K_S.gguf b/Llama-PLLuM-8B-base-250801.Q4_K_S.gguf new file mode 100644 index 0000000..76b3162 --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b92111e86c67dd141db64f19ec30b0bef3f0ca2238ff1c58b8bec73330d89b0 +size 4692669536 diff --git a/Llama-PLLuM-8B-base-250801.Q5_K_M.gguf b/Llama-PLLuM-8B-base-250801.Q5_K_M.gguf new file mode 100644 index 0000000..be375d1 --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8679bf223c124403e5de9d7c7d883dc301be0b07abfb9caee5afe47e18b249f3 +size 5732988000 diff --git a/Llama-PLLuM-8B-base-250801.Q5_K_S.gguf b/Llama-PLLuM-8B-base-250801.Q5_K_S.gguf new file mode 100644 index 0000000..b88907f --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33764811a4807f72ae285d6c6badf2d3870411b877aaf08622b162a15f3f913b +size 5599294560 diff --git a/Llama-PLLuM-8B-base-250801.Q6_K.gguf b/Llama-PLLuM-8B-base-250801.Q6_K.gguf new file mode 100644 index 0000000..95c799f --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cacc0d9f71c53862764894fc7f5e07d60a991e9e0e2fdd59fa5931f20d93b1b +size 6596007008 diff --git a/Llama-PLLuM-8B-base-250801.Q8_0.gguf b/Llama-PLLuM-8B-base-250801.Q8_0.gguf new file mode 100644 index 0000000..10e77d6 --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43e3465236514bcc69ac5e8c60d536a11e0f8191c2faaa5dec04881e6e688ebd +size 8540771424 diff --git a/Llama-PLLuM-8B-base-250801.f16.gguf b/Llama-PLLuM-8B-base-250801.f16.gguf new file mode 100644 index 0000000..afc92ad --- /dev/null +++ b/Llama-PLLuM-8B-base-250801.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d128b349abdba778952816fc350f755ab64761cf194a1ea5bce0f8576cb88b +size 16068891744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5f67b1a --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: CYFRAGOVPL/Llama-PLLuM-8B-base-2508 +language: +- pl +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/CYFRAGOVPL/Llama-PLLuM-8B-base-2508 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-PLLuM-8B-base-250801-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-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/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-250801-GGUF/resolve/main/Llama-PLLuM-8B-base-250801.f16.gguf) | f16 | 16.2 | 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. + +