commit 1dfae0f79b55952e74caa2ed5d0dbcb51a974d61 Author: ModelHub XC Date: Wed Jun 3 18:19:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PLLuM-12B-instruct-2412-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..83e8a9f --- /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-instruct-2412.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PLLuM-12B-instruct-2412.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PLLuM-12B-instruct-2412.IQ4_XS.gguf b/PLLuM-12B-instruct-2412.IQ4_XS.gguf new file mode 100644 index 0000000..004b0b6 --- /dev/null +++ b/PLLuM-12B-instruct-2412.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef262b265e9e199c862ae55fffe40badb02401e39ac4850f0dc76974f24a43b +size 6800054400 diff --git a/PLLuM-12B-instruct-2412.Q2_K.gguf b/PLLuM-12B-instruct-2412.Q2_K.gguf new file mode 100644 index 0000000..203b649 --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e83e47485d5ab07206ce15ae2b1803a21f04d6ad9f1ba1d3a19158e0f7c8fd0 +size 4791048320 diff --git a/PLLuM-12B-instruct-2412.Q3_K_L.gguf b/PLLuM-12B-instruct-2412.Q3_K_L.gguf new file mode 100644 index 0000000..61d7c3c --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bae12829f6a7f491381dd34e25dae195e5515596e4d12673f5530aa616be9c62 +size 6561503360 diff --git a/PLLuM-12B-instruct-2412.Q3_K_M.gguf b/PLLuM-12B-instruct-2412.Q3_K_M.gguf new file mode 100644 index 0000000..681b1e5 --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:491f24ae0a64f32cbe6d06b97d3dd6333445e0b2ab355adeab6ea9002da68b08 +size 6083090560 diff --git a/PLLuM-12B-instruct-2412.Q3_K_S.gguf b/PLLuM-12B-instruct-2412.Q3_K_S.gguf new file mode 100644 index 0000000..b194046 --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a02328ca25694738b689e56a29e4abbff253251492f8432735399dd45fcb95 +size 5534226560 diff --git a/PLLuM-12B-instruct-2412.Q4_K_M.gguf b/PLLuM-12B-instruct-2412.Q4_K_M.gguf new file mode 100644 index 0000000..08305b4 --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c2c3581a062f74b3b8d9bea97705239f62ebbf52ebcb95b5b9368bc2a654e4d +size 7477205120 diff --git a/PLLuM-12B-instruct-2412.Q4_K_S.gguf b/PLLuM-12B-instruct-2412.Q4_K_S.gguf new file mode 100644 index 0000000..6c030fd --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128c0b9d4a31928a902427d47b97adaf0ac36fdfb95464f63f30e8a1ada82921 +size 7120197760 diff --git a/PLLuM-12B-instruct-2412.Q5_K_M.gguf b/PLLuM-12B-instruct-2412.Q5_K_M.gguf new file mode 100644 index 0000000..09bdef6 --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4b9c35f1f3f9cd4f49d0cc74be02c946de3afd8be89b486c882269795e1385c +size 8727632000 diff --git a/PLLuM-12B-instruct-2412.Q5_K_S.gguf b/PLLuM-12B-instruct-2412.Q5_K_S.gguf new file mode 100644 index 0000000..ba7b377 --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e33fd01569884dcb1f67134e0be82edac8a39e8632e844a89034f887705a459 +size 8518736000 diff --git a/PLLuM-12B-instruct-2412.Q6_K.gguf b/PLLuM-12B-instruct-2412.Q6_K.gguf new file mode 100644 index 0000000..d3f1710 --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:117dcbadf1cd99b06c93a9ae08ceed5a3125ac2590e129d4bfe31c093f7bcba5 +size 10056210560 diff --git a/PLLuM-12B-instruct-2412.Q8_0.gguf b/PLLuM-12B-instruct-2412.Q8_0.gguf new file mode 100644 index 0000000..eb00c66 --- /dev/null +++ b/PLLuM-12B-instruct-2412.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a91fd408074c0e1151cd7ad8fcb9b00e0cf26a56b85c0a373e6a96fe232f699 +size 13022369920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e5542be --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: CYFRAGOVPL/PLLuM-12B-instruct-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-instruct-2412 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PLLuM-12B-instruct-2412-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/PLLuM-12B-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/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.Q3_K_S.gguf) | Q3_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.Q3_K_L.gguf) | Q3_K_L | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.IQ4_XS.gguf) | IQ4_XS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.Q5_K_S.gguf) | Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.Q5_K_M.gguf) | Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-2412.Q6_K.gguf) | Q6_K | 10.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-GGUF/resolve/main/PLLuM-12B-instruct-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. + +