commit 5726a56e31315157b1d9d81671d581361feff339 Author: ModelHub XC Date: Fri Sep 4 14:26:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bda58c9 --- /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 +SparseLlama-3-8B-pruned_50.2of4.f16.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SparseLlama-3-8B-pruned_50.2of4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1399fee --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: RedHatAI/SparseLlama-3-8B-pruned_50.2of4 +language: +- en +library_name: transformers +model_type: llama +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- sparse +--- +## About + + + + + + +static quants of https://huggingface.co/RedHatAI/SparseLlama-3-8B-pruned_50.2of4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SparseLlama-3-8B-pruned_50.2of4-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SparseLlama-3-8B-pruned_50.2of4-GGUF/resolve/main/SparseLlama-3-8B-pruned_50.2of4.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. + + diff --git a/SparseLlama-3-8B-pruned_50.2of4.IQ4_XS.gguf b/SparseLlama-3-8B-pruned_50.2of4.IQ4_XS.gguf new file mode 100644 index 0000000..cdb6698 --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91cf01f4d28e3455685ae051354eea07c24b56c5d45f8b01469dc7af7d5f44b9 +size 4484363072 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q2_K.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q2_K.gguf new file mode 100644 index 0000000..43bc9f9 --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d607d49d88219e1f8db1ad068cb3b0859b3c79611756fff2331f31deaa6ffe6 +size 3179131712 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q3_K_L.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q3_K_L.gguf new file mode 100644 index 0000000..96416ac --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55207cd248c6c76be32780f24ab5ddd419f1cdfeae8298d5caf14e5a93efc456 +size 4321956672 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q3_K_M.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q3_K_M.gguf new file mode 100644 index 0000000..f3e0606 --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d46c21fe82197b80e172b3ef2ecdbe2e3742485adfed642c2bb4cffadd553d97 +size 4018918208 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q3_K_S.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q3_K_S.gguf new file mode 100644 index 0000000..0faf6fe --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f481d39bce4a51be791e46184a7923248452616fd2739dddf7713e4d56a8067b +size 3664499520 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q4_K_M.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q4_K_M.gguf new file mode 100644 index 0000000..1f7c016 --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4150014eb1b9f816f04914daff8d19af1f1c9a536ff13bc2a953442c9467b43 +size 4920734528 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q4_K_S.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q4_K_S.gguf new file mode 100644 index 0000000..c425971 --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81785eb0737669c6930496cdfe013b3bc07a4ab038f3410c063ff8e5de70d5a0 +size 4692669248 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q5_K_M.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q5_K_M.gguf new file mode 100644 index 0000000..2e9c75f --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a556f171642911db59f88e46f13dee934eb82f5d4625e91c3b008e0eb19ad8 +size 5732987712 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q5_K_S.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q5_K_S.gguf new file mode 100644 index 0000000..8175a20 --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2878eb67f14fdf13410bb01223460acadc88ff6caf6fec2439036ed715070452 +size 5599294272 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q6_K.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q6_K.gguf new file mode 100644 index 0000000..bfe7228 --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d87059e8d821ad00905e11fce8bca6a31ae1316b50279785a815dc22ca815690 +size 6596006720 diff --git a/SparseLlama-3-8B-pruned_50.2of4.Q8_0.gguf b/SparseLlama-3-8B-pruned_50.2of4.Q8_0.gguf new file mode 100644 index 0000000..6dbd9e0 --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15911ce82832a5f36e2b581864512ff1f1a5b9a4a318512301fbdf8ed1af2b52 +size 8540771136 diff --git a/SparseLlama-3-8B-pruned_50.2of4.f16.gguf b/SparseLlama-3-8B-pruned_50.2of4.f16.gguf new file mode 100644 index 0000000..1cd2f06 --- /dev/null +++ b/SparseLlama-3-8B-pruned_50.2of4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836d3cc200b3eb2b9245c17e63c3fe2ad63e18e9d4c89947baca8cbe2cc24007 +size 16068891456