commit 69f65e448104362c2e2894e3feccdd24f457cd3e Author: ModelHub XC Date: Thu Jul 16 17:39:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SFT-Compo-Distill-Llama-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..65afff2 --- /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 +SFT-Compo-Distill-Llama-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SFT-Compo-Distill-Llama-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3e05a81 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: LoRe-Team/SFT-Compo-Distill-Llama-8B +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + + + + +static quants of https://huggingface.co/LoRe-Team/SFT-Compo-Distill-Llama-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SFT-Compo-Distill-Llama-8B-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/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SFT-Compo-Distill-Llama-8B-GGUF/resolve/main/SFT-Compo-Distill-Llama-8B.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/SFT-Compo-Distill-Llama-8B.IQ4_XS.gguf b/SFT-Compo-Distill-Llama-8B.IQ4_XS.gguf new file mode 100644 index 0000000..7781051 --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633c74e0675e8de4fac627a3a1a24b9b0756e448786b9212a21548d4d0e62a3f +size 4484365984 diff --git a/SFT-Compo-Distill-Llama-8B.Q2_K.gguf b/SFT-Compo-Distill-Llama-8B.Q2_K.gguf new file mode 100644 index 0000000..d380e30 --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95447ef1a7bbb2c91cc2d6923577653c1446a56896c2c0d2be03d4f9aac8c98a +size 3179134624 diff --git a/SFT-Compo-Distill-Llama-8B.Q3_K_L.gguf b/SFT-Compo-Distill-Llama-8B.Q3_K_L.gguf new file mode 100644 index 0000000..fc19a8c --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be45045e7d15da7d27cef5d3753aae010998d434f9286edbecb66ad1493dad8 +size 4321959584 diff --git a/SFT-Compo-Distill-Llama-8B.Q3_K_M.gguf b/SFT-Compo-Distill-Llama-8B.Q3_K_M.gguf new file mode 100644 index 0000000..c680b1a --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd93b2c7af693e6bbbd2fbf32b952858bab79224e0ba136e6f8ed4181e1c4e6 +size 4018921120 diff --git a/SFT-Compo-Distill-Llama-8B.Q3_K_S.gguf b/SFT-Compo-Distill-Llama-8B.Q3_K_S.gguf new file mode 100644 index 0000000..853ee4b --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24677922c7dd6ec0ac943bd4a56cc29b8373243731f1fdb2d4c029962e7c971d +size 3664502432 diff --git a/SFT-Compo-Distill-Llama-8B.Q4_K_M.gguf b/SFT-Compo-Distill-Llama-8B.Q4_K_M.gguf new file mode 100644 index 0000000..1445ace --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aed957ddbec10cb4684d15bfeed5d88d819d5c16ee37f37b41d2d2b562eb6ac +size 4920737440 diff --git a/SFT-Compo-Distill-Llama-8B.Q4_K_S.gguf b/SFT-Compo-Distill-Llama-8B.Q4_K_S.gguf new file mode 100644 index 0000000..ca89560 --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec62a0affd5054e6efdc3ae975cd62272b063ec79aa201da8bb8e6e3fe46340 +size 4692672160 diff --git a/SFT-Compo-Distill-Llama-8B.Q5_K_M.gguf b/SFT-Compo-Distill-Llama-8B.Q5_K_M.gguf new file mode 100644 index 0000000..2a6656b --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad147bb9654cc6cb04010861d2aed64e3a3ce92d784c3355fdaf593e8de3883 +size 5732990624 diff --git a/SFT-Compo-Distill-Llama-8B.Q5_K_S.gguf b/SFT-Compo-Distill-Llama-8B.Q5_K_S.gguf new file mode 100644 index 0000000..743bca9 --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17b3a9ea0cf6f37765fd0e3ad318e80043924114ccb998c4b69d14edf8d9c30 +size 5599297184 diff --git a/SFT-Compo-Distill-Llama-8B.Q6_K.gguf b/SFT-Compo-Distill-Llama-8B.Q6_K.gguf new file mode 100644 index 0000000..90f6822 --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab5d8072de1ad90365520c1a2a3b9b3daf74cf3a159cf27e083c061226d20de +size 6596009632 diff --git a/SFT-Compo-Distill-Llama-8B.Q8_0.gguf b/SFT-Compo-Distill-Llama-8B.Q8_0.gguf new file mode 100644 index 0000000..ae495ef --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f59ae2f920416b859709b0328bac32ff6c9c283fa2c1fac52cd9d01878ff18 +size 8540774048 diff --git a/SFT-Compo-Distill-Llama-8B.f16.gguf b/SFT-Compo-Distill-Llama-8B.f16.gguf new file mode 100644 index 0000000..698d080 --- /dev/null +++ b/SFT-Compo-Distill-Llama-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f46270c4d0257c8c2d4314ec2a9883ca21d12e2ecc2a1018696ba8dacf9fe01 +size 16068894368