commit 0ff3af523a017cb5d8091446fae8f39b9114b208 Author: ModelHub XC Date: Tue Jun 16 01:52:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PLLuM-4B-base-2512-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5f92ef0 --- /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 +PLLuM-4B-base-2512.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-4B-base-2512.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PLLuM-4B-base-2512.IQ4_XS.gguf b/PLLuM-4B-base-2512.IQ4_XS.gguf new file mode 100644 index 0000000..fe41b4e --- /dev/null +++ b/PLLuM-4B-base-2512.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4230ac3a2dbc182aca5b158278ba8e7f8e0baabd07775b184c9c6890e43e328 +size 2279624704 diff --git a/PLLuM-4B-base-2512.Q2_K.gguf b/PLLuM-4B-base-2512.Q2_K.gguf new file mode 100644 index 0000000..964397b --- /dev/null +++ b/PLLuM-4B-base-2512.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a8014ebd105f8d3a366a066c0754e4da080820d8bb34b3b6225b737d2732a6d +size 1729163264 diff --git a/PLLuM-4B-base-2512.Q3_K_L.gguf b/PLLuM-4B-base-2512.Q3_K_L.gguf new file mode 100644 index 0000000..39636e3 --- /dev/null +++ b/PLLuM-4B-base-2512.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:375acdda88d44315eacd4a769c5e1e47f03b49c373a3242f854a608420ac7c42 +size 2236084224 diff --git a/PLLuM-4B-base-2512.Q3_K_M.gguf b/PLLuM-4B-base-2512.Q3_K_M.gguf new file mode 100644 index 0000000..73fff6c --- /dev/null +++ b/PLLuM-4B-base-2512.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a6c5ecc3c63d1d7f06a4c9fcbe753d9f3edf1a459b112bd92b23cd665a528c6 +size 2098458624 diff --git a/PLLuM-4B-base-2512.Q3_K_S.gguf b/PLLuM-4B-base-2512.Q3_K_S.gguf new file mode 100644 index 0000000..91eb2ed --- /dev/null +++ b/PLLuM-4B-base-2512.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e832515c74c08725594e2e15fc758bdb34f623a7f9c140f3033de0947afac516 +size 1937362944 diff --git a/PLLuM-4B-base-2512.Q4_K_M.gguf b/PLLuM-4B-base-2512.Q4_K_M.gguf new file mode 100644 index 0000000..ee66ec5 --- /dev/null +++ b/PLLuM-4B-base-2512.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a04368f55bd0a46668cd77da5e177d4c91a09408c63c40cf0316630072d1765 +size 2489892864 diff --git a/PLLuM-4B-base-2512.Q4_K_S.gguf b/PLLuM-4B-base-2512.Q4_K_S.gguf new file mode 100644 index 0000000..87e0aea --- /dev/null +++ b/PLLuM-4B-base-2512.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3cb0d96c1f4fe282e49021b897d2e8c7d19723d4339bc6ed17f583b411bc042 +size 2377928704 diff --git a/PLLuM-4B-base-2512.Q5_K_M.gguf b/PLLuM-4B-base-2512.Q5_K_M.gguf new file mode 100644 index 0000000..fc2dcc2 --- /dev/null +++ b/PLLuM-4B-base-2512.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19eaf83c6181750082f1a871157fd8579acc277452446c87adf8fe6eb3d2038d +size 2829697024 diff --git a/PLLuM-4B-base-2512.Q5_K_S.gguf b/PLLuM-4B-base-2512.Q5_K_S.gguf new file mode 100644 index 0000000..b336ca2 --- /dev/null +++ b/PLLuM-4B-base-2512.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47abf3975f11958490e4a35f5ac15ed6c1a8c32f86cc5e8fef9e807c58e98ee6 +size 2764591104 diff --git a/PLLuM-4B-base-2512.Q6_K.gguf b/PLLuM-4B-base-2512.Q6_K.gguf new file mode 100644 index 0000000..bae8270 --- /dev/null +++ b/PLLuM-4B-base-2512.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c835eb0cb723899d6ec020543e1d49920bebd3cede6bd6940b679659e5aa8f6a +size 3190738944 diff --git a/PLLuM-4B-base-2512.Q8_0.gguf b/PLLuM-4B-base-2512.Q8_0.gguf new file mode 100644 index 0000000..822049f --- /dev/null +++ b/PLLuM-4B-base-2512.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea4c22f13c34804f452d91473e68ad7d35381032969c7a2941e2b93df4d396ea +size 4130401024 diff --git a/PLLuM-4B-base-2512.f16.gguf b/PLLuM-4B-base-2512.f16.gguf new file mode 100644 index 0000000..ca5233a --- /dev/null +++ b/PLLuM-4B-base-2512.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3466e832c8b44acbad53963b6ddfea7b83e291e99e6f15dd423a3a975cf51158 +size 7767802624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f92e91c --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: CYFRAGOVPL/PLLuM-4B-base-2512 +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-4B-base-2512 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PLLuM-4B-base-2512-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/PLLuM-4B-base-2512-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-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-4B-base-2512-GGUF/resolve/main/PLLuM-4B-base-2512.f16.gguf) | f16 | 7.9 | 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. + +