commit 887c6302a75391d2075c7f0c67d3e96231d0c07c Author: ModelHub XC Date: Fri Jun 26 23:58:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Lama3.1-8B-Saver-16B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..252ba62 --- /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 +Lama3.1-8B-Saver-16B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lama3.1-8B-Saver-16B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Lama3.1-8B-Saver-16B.IQ4_XS.gguf b/Lama3.1-8B-Saver-16B.IQ4_XS.gguf new file mode 100644 index 0000000..4dbfb53 --- /dev/null +++ b/Lama3.1-8B-Saver-16B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71fb89ea59644d35b1082caca44ceb6fc95ce00df5b22570a9b22e6844bc139 +size 4484363936 diff --git a/Lama3.1-8B-Saver-16B.Q2_K.gguf b/Lama3.1-8B-Saver-16B.Q2_K.gguf new file mode 100644 index 0000000..b11ac85 --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f81e9e83dd145959d057c7ae5c603aeca89303860e523cb68433cf211097fd +size 3179132576 diff --git a/Lama3.1-8B-Saver-16B.Q3_K_L.gguf b/Lama3.1-8B-Saver-16B.Q3_K_L.gguf new file mode 100644 index 0000000..1eb2fef --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168ba8cff485b319f7d9db319e27ba3f5e3707704fafec7c1a4a132c8475ce13 +size 4321957536 diff --git a/Lama3.1-8B-Saver-16B.Q3_K_M.gguf b/Lama3.1-8B-Saver-16B.Q3_K_M.gguf new file mode 100644 index 0000000..52754e6 --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdc1e9623c6e1a364fa3866db8ed50c42a22f85cfe69e3c306f10959b48d2305 +size 4018919072 diff --git a/Lama3.1-8B-Saver-16B.Q3_K_S.gguf b/Lama3.1-8B-Saver-16B.Q3_K_S.gguf new file mode 100644 index 0000000..029131e --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e64957ce87a2c7f09f4707b90ee2e10e11af5585174edd23b3aebe7c08f7997 +size 3664500384 diff --git a/Lama3.1-8B-Saver-16B.Q4_K_M.gguf b/Lama3.1-8B-Saver-16B.Q4_K_M.gguf new file mode 100644 index 0000000..b99517c --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fb7ae84a89845325719f21b5b3d9d3fe009be163aff79f7025805199785b87 +size 4920735392 diff --git a/Lama3.1-8B-Saver-16B.Q4_K_S.gguf b/Lama3.1-8B-Saver-16B.Q4_K_S.gguf new file mode 100644 index 0000000..60940c2 --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5775b652088fc49b795faabd29a3a4dda820004735bdccd4c047c6f96c8161 +size 4692670112 diff --git a/Lama3.1-8B-Saver-16B.Q5_K_M.gguf b/Lama3.1-8B-Saver-16B.Q5_K_M.gguf new file mode 100644 index 0000000..607c0eb --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad6c159b8850e79502131e43929d5615997df9e725b954ac3bc2f533093acd2 +size 5732988576 diff --git a/Lama3.1-8B-Saver-16B.Q5_K_S.gguf b/Lama3.1-8B-Saver-16B.Q5_K_S.gguf new file mode 100644 index 0000000..81b1fc4 --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:172441a4364cd53fb42edaa2af3d05fe5fdbd7b54fde41004b8614e11cf9757f +size 5599295136 diff --git a/Lama3.1-8B-Saver-16B.Q6_K.gguf b/Lama3.1-8B-Saver-16B.Q6_K.gguf new file mode 100644 index 0000000..11937fe --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffa6c840549ba843899dabd5eb08fbec2181b8f49f21f60b1ad0885840b31b8 +size 6596007584 diff --git a/Lama3.1-8B-Saver-16B.Q8_0.gguf b/Lama3.1-8B-Saver-16B.Q8_0.gguf new file mode 100644 index 0000000..47a9f08 --- /dev/null +++ b/Lama3.1-8B-Saver-16B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc1f0338319019e9b0860ceb65bc634adda544333760bcb725dbd3dfc8c5cce +size 8540772000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aa2bafa --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: RsGoksel/Lama3.1-8B-Saver-16B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/RsGoksel/Lama3.1-8B-Saver-16B + + +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/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Lama3.1-8B-Saver-16B-GGUF/resolve/main/Lama3.1-8B-Saver-16B.Q8_0.gguf) | Q8_0 | 8.6 | 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. + +