commit a82542cccb9614b42833a857b2ebf06e7c0250cc Author: ModelHub XC Date: Sun May 31 23:07:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-PLLuM-8B-base-2508-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4ffffb4 --- /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-2508.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-PLLuM-8B-base-2508.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-PLLuM-8B-base-2508.IQ4_XS.gguf b/Llama-PLLuM-8B-base-2508.IQ4_XS.gguf new file mode 100644 index 0000000..e6ede2d --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebce87a7277ddb2e0e4f3b331085bf5fe04cac473335f6f4b8da10330345393 +size 4484363424 diff --git a/Llama-PLLuM-8B-base-2508.Q2_K.gguf b/Llama-PLLuM-8B-base-2508.Q2_K.gguf new file mode 100644 index 0000000..b03cf2b --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6d1a46763e2e29d9c6ed101936511c453dd1ef13c7a86491803282c752697e +size 3179132064 diff --git a/Llama-PLLuM-8B-base-2508.Q3_K_L.gguf b/Llama-PLLuM-8B-base-2508.Q3_K_L.gguf new file mode 100644 index 0000000..6cc632c --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:461d6d89b3604ba76572d3089591b0f557b995d5f3b8f3f95b73328236802963 +size 4321957024 diff --git a/Llama-PLLuM-8B-base-2508.Q3_K_M.gguf b/Llama-PLLuM-8B-base-2508.Q3_K_M.gguf new file mode 100644 index 0000000..bcba2b5 --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf20b3126ca7aad9c04c432c199d816f3768461d0e98eaab91f8dda8d9a4ec3 +size 4018918560 diff --git a/Llama-PLLuM-8B-base-2508.Q3_K_S.gguf b/Llama-PLLuM-8B-base-2508.Q3_K_S.gguf new file mode 100644 index 0000000..19bec43 --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6a21cf30c7e1e637137eafed4b4b700d1419e29e6833a828bc7f6ee59c6409f +size 3664499872 diff --git a/Llama-PLLuM-8B-base-2508.Q4_K_M.gguf b/Llama-PLLuM-8B-base-2508.Q4_K_M.gguf new file mode 100644 index 0000000..6079061 --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f19497c198b4cf2f7ac3ea3c5268b6b59d671bc7d78911e62b2888925a411799 +size 4920734880 diff --git a/Llama-PLLuM-8B-base-2508.Q4_K_S.gguf b/Llama-PLLuM-8B-base-2508.Q4_K_S.gguf new file mode 100644 index 0000000..a150093 --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05dc6213b5746c1299e79e77533ff642ea14ecacdfa0438248001a194279ed3d +size 4692669600 diff --git a/Llama-PLLuM-8B-base-2508.Q5_K_M.gguf b/Llama-PLLuM-8B-base-2508.Q5_K_M.gguf new file mode 100644 index 0000000..a5340f6 --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2bff0e0b8a7bed73d543693477d34ffa8e6aa0dd9918d8b4c89179a81747651 +size 5732988064 diff --git a/Llama-PLLuM-8B-base-2508.Q5_K_S.gguf b/Llama-PLLuM-8B-base-2508.Q5_K_S.gguf new file mode 100644 index 0000000..a57f23f --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1acac493edd0c10ad1c42528ffd412ab3efb1f5a459e4a14c118b7284e9e2832 +size 5599294624 diff --git a/Llama-PLLuM-8B-base-2508.Q6_K.gguf b/Llama-PLLuM-8B-base-2508.Q6_K.gguf new file mode 100644 index 0000000..222d6e5 --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbbc439c620081237b5a9aba2d560e07b73e9fa38c6a121450b6968bc69d8575 +size 6596007072 diff --git a/Llama-PLLuM-8B-base-2508.Q8_0.gguf b/Llama-PLLuM-8B-base-2508.Q8_0.gguf new file mode 100644 index 0000000..66cdd7e --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b15cd2df588822c6249433549df5c0ae9c8363541b652721b7176d139c7beb +size 8540771488 diff --git a/Llama-PLLuM-8B-base-2508.f16.gguf b/Llama-PLLuM-8B-base-2508.f16.gguf new file mode 100644 index 0000000..601fa04 --- /dev/null +++ b/Llama-PLLuM-8B-base-2508.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae740729dd10adc0adc9bde1a5f3ca6481e123920d3736757aa926602c5fc31f +size 16068891808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e17a87e --- /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-2508-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-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-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-PLLuM-8B-base-2508-GGUF/resolve/main/Llama-PLLuM-8B-base-2508.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. + +