commit 1e04084916dba73c1c82418ec1b0769e4722fcc1 Author: ModelHub XC Date: Mon Jun 1 03:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5f4743c --- /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-instruct-2412.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-instruct-2412.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-PLLuM-8B-instruct-2412.IQ4_XS.gguf b/Llama-PLLuM-8B-instruct-2412.IQ4_XS.gguf new file mode 100644 index 0000000..41e0207 --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f600e7e25690f8553a1367cd1afe7586fec94202d57fe0ba621fd635fc70d856 +size 4484375616 diff --git a/Llama-PLLuM-8B-instruct-2412.Q2_K.gguf b/Llama-PLLuM-8B-instruct-2412.Q2_K.gguf new file mode 100644 index 0000000..590000a --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0905aef24a247e7b7d51981fbe412e66943303f9b97af66696fb5a3e9e06ed +size 3179142592 diff --git a/Llama-PLLuM-8B-instruct-2412.Q3_K_L.gguf b/Llama-PLLuM-8B-instruct-2412.Q3_K_L.gguf new file mode 100644 index 0000000..e15960b --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53870da595db41658473ab65748bbc7b9eed72a56b08f8e958060e70fefe302a +size 4321968384 diff --git a/Llama-PLLuM-8B-instruct-2412.Q3_K_M.gguf b/Llama-PLLuM-8B-instruct-2412.Q3_K_M.gguf new file mode 100644 index 0000000..3e1e81d --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5fd6eff43aa95360db21cf2bf0232d9b1ba746aba2d09238821bd745421d85 +size 4018929920 diff --git a/Llama-PLLuM-8B-instruct-2412.Q3_K_S.gguf b/Llama-PLLuM-8B-instruct-2412.Q3_K_S.gguf new file mode 100644 index 0000000..94d6ace --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:291a2bf6a934b33feaae99d91116f84f6c7a2fe32f20e66f612b800d5b2bf850 +size 3664511232 diff --git a/Llama-PLLuM-8B-instruct-2412.Q4_K_M.gguf b/Llama-PLLuM-8B-instruct-2412.Q4_K_M.gguf new file mode 100644 index 0000000..853c568 --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1de7173b94fbddc88a60c9fb461d03e28433b8e6bb2f0e294d5e24df03b95089 +size 4920747328 diff --git a/Llama-PLLuM-8B-instruct-2412.Q4_K_S.gguf b/Llama-PLLuM-8B-instruct-2412.Q4_K_S.gguf new file mode 100644 index 0000000..c2073fc --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a313500a66d517a8ebe5ca8a17d09d0f7daa07a3e216ff1856970bd244728124 +size 4692682048 diff --git a/Llama-PLLuM-8B-instruct-2412.Q5_K_M.gguf b/Llama-PLLuM-8B-instruct-2412.Q5_K_M.gguf new file mode 100644 index 0000000..ce54089 --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8329236ae5c23c84396cc25f69e274d8783839c41e5a1530c3c27f6f15fdcce5 +size 5733001536 diff --git a/Llama-PLLuM-8B-instruct-2412.Q5_K_S.gguf b/Llama-PLLuM-8B-instruct-2412.Q5_K_S.gguf new file mode 100644 index 0000000..7a3c2fa --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02843936cc7f3e886960811c7c2b0d3988e21401f8e9408de652a93630363f97 +size 5599308096 diff --git a/Llama-PLLuM-8B-instruct-2412.Q6_K.gguf b/Llama-PLLuM-8B-instruct-2412.Q6_K.gguf new file mode 100644 index 0000000..1636889 --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd1a1b793cb24f00d8f3d1c708818cb939092a6cb7900f918d4644a7772e5180 +size 6596021632 diff --git a/Llama-PLLuM-8B-instruct-2412.Q8_0.gguf b/Llama-PLLuM-8B-instruct-2412.Q8_0.gguf new file mode 100644 index 0000000..a0ef335 --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23a9d7227cd9ae1290f750c7c748c82abe2568bb6ce7cacfac6342f44f42a99b +size 8540790016 diff --git a/Llama-PLLuM-8B-instruct-2412.f16.gguf b/Llama-PLLuM-8B-instruct-2412.f16.gguf new file mode 100644 index 0000000..d84de56 --- /dev/null +++ b/Llama-PLLuM-8B-instruct-2412.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d870a7d8b711eb331db67add54ee4562f427a5379a87579d8d4668bfa79e76a4 +size 16068925696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1fa7f48 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: CYFRAGOVPL/Llama-PLLuM-8B-instruct-2412 +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-instruct-2412 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-PLLuM-8B-instruct-2412-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-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/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-instruct-2412-GGUF/resolve/main/Llama-PLLuM-8B-instruct-2412.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. + +