commit eafdaa66e6c2b67b58bd193a65f2f4ba1d7f0d07 Author: ModelHub XC Date: Tue Jun 2 10:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-PLLuM-8B-base-2412-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bce6cde --- /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-2412.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2412.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-PLLuM-8B-base-2412.IQ4_XS.gguf b/Llama-PLLuM-8B-base-2412.IQ4_XS.gguf new file mode 100644 index 0000000..52202c8 --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eadf5035d6c538efa85a83a4f3391f1b8597f83f94f815151743e96ecbca389 +size 4484363360 diff --git a/Llama-PLLuM-8B-base-2412.Q2_K.gguf b/Llama-PLLuM-8B-base-2412.Q2_K.gguf new file mode 100644 index 0000000..baf1dbe --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f6261d903f6165e5265bc332ed0c24984c9ee0fd2c14048442d7e20a86cf3a4 +size 3179132000 diff --git a/Llama-PLLuM-8B-base-2412.Q3_K_L.gguf b/Llama-PLLuM-8B-base-2412.Q3_K_L.gguf new file mode 100644 index 0000000..61471ef --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc8adcd3588e0c9a74a3a7e64e83a2d7d9544fc232e10e2a5b615a74c17c52bf +size 4321956960 diff --git a/Llama-PLLuM-8B-base-2412.Q3_K_M.gguf b/Llama-PLLuM-8B-base-2412.Q3_K_M.gguf new file mode 100644 index 0000000..4e61fed --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634537a71777391f6bd0775f159dbed071b12c3f37d43c489156052137315d38 +size 4018918496 diff --git a/Llama-PLLuM-8B-base-2412.Q3_K_S.gguf b/Llama-PLLuM-8B-base-2412.Q3_K_S.gguf new file mode 100644 index 0000000..526a7a5 --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cdb8dfecac89ea82eca73468ba9bc62bc827748fca6b2c60b3699fda17eda03 +size 3664499808 diff --git a/Llama-PLLuM-8B-base-2412.Q4_K_M.gguf b/Llama-PLLuM-8B-base-2412.Q4_K_M.gguf new file mode 100644 index 0000000..c3d8b73 --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c28d7bf9b1501e005622b1bc8e40e38f1516cdbbc9a109695fabb8f4a79ca8 +size 4920734816 diff --git a/Llama-PLLuM-8B-base-2412.Q4_K_S.gguf b/Llama-PLLuM-8B-base-2412.Q4_K_S.gguf new file mode 100644 index 0000000..74877f1 --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:938a7969aab4c128165abecc1a0c48627eb640b0daae2a163f2192748dfc7cfb +size 4692669536 diff --git a/Llama-PLLuM-8B-base-2412.Q5_K_M.gguf b/Llama-PLLuM-8B-base-2412.Q5_K_M.gguf new file mode 100644 index 0000000..31635ab --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5767638234ead9383bb82a5e25f7233db31bbe220ffd011d6d70a2c5790fb62f +size 5732988000 diff --git a/Llama-PLLuM-8B-base-2412.Q5_K_S.gguf b/Llama-PLLuM-8B-base-2412.Q5_K_S.gguf new file mode 100644 index 0000000..99a1ca6 --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23c6d7b29815ebae5cb028f96128856e4e44133d57c8f3b7c5e3dae8534aeff3 +size 5599294560 diff --git a/Llama-PLLuM-8B-base-2412.Q6_K.gguf b/Llama-PLLuM-8B-base-2412.Q6_K.gguf new file mode 100644 index 0000000..28005dd --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4311e85c9814b73f8f0763edd22d62a8143b9d211ea488d2141ca8eb268c7d3e +size 6596007008 diff --git a/Llama-PLLuM-8B-base-2412.Q8_0.gguf b/Llama-PLLuM-8B-base-2412.Q8_0.gguf new file mode 100644 index 0000000..ef503f7 --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb5b462f37a943775ef5eb29f976b77866a0a69b6dd907c0a319ed4b1d7af7f +size 8540771424 diff --git a/Llama-PLLuM-8B-base-2412.f16.gguf b/Llama-PLLuM-8B-base-2412.f16.gguf new file mode 100644 index 0000000..51e2a10 --- /dev/null +++ b/Llama-PLLuM-8B-base-2412.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee42dc57c52ce315d5cc77d4b64143279be40f79fcdbbe2a9b589ae2056f97d +size 16068891744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6b0a6de --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: CYFRAGOVPL/Llama-PLLuM-8B-base-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-base-2412 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-PLLuM-8B-base-2412-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-PLLuM-8B-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/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-2412.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2412-GGUF/resolve/main/Llama-PLLuM-8B-base-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. + +