commit eb384bade91193d286f5c48c5ba7e4b30ac067a0 Author: ModelHub XC Date: Wed Sep 30 06:31:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KONI-Llama3.1-8B-20240824-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f31cc92 --- /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 +KONI-Llama3.1-8B-20240824.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.f16.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-20240824.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KONI-Llama3.1-8B-20240824.IQ4_XS.gguf b/KONI-Llama3.1-8B-20240824.IQ4_XS.gguf new file mode 100644 index 0000000..2d06152 --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8aa399b5e4b8275c7f2d1f5fc155da2c844a0f10fbbedc4435c40186fdda90d +size 4484363008 diff --git a/KONI-Llama3.1-8B-20240824.Q2_K.gguf b/KONI-Llama3.1-8B-20240824.Q2_K.gguf new file mode 100644 index 0000000..174e011 --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f51344edf3475c38b3b17544819296c9f97e0e4f05a9d7502b099660ea645b7 +size 3179131648 diff --git a/KONI-Llama3.1-8B-20240824.Q3_K_L.gguf b/KONI-Llama3.1-8B-20240824.Q3_K_L.gguf new file mode 100644 index 0000000..c1ac7f6 --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dddaaf703e0276d4de38a689d4aefb2702c75290a4859cff7e4e55e17a97d02f +size 4321956608 diff --git a/KONI-Llama3.1-8B-20240824.Q3_K_M.gguf b/KONI-Llama3.1-8B-20240824.Q3_K_M.gguf new file mode 100644 index 0000000..3aa8c9e --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e2c2bc6b8572df971d3c88d3e08e24c3788fa27067e2279f9d066eb18a92e54 +size 4018918144 diff --git a/KONI-Llama3.1-8B-20240824.Q3_K_S.gguf b/KONI-Llama3.1-8B-20240824.Q3_K_S.gguf new file mode 100644 index 0000000..32e090d --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72f2d78675a4ad8fe2d72cd3e959a7b78cf2551c97a48202626aba2b05b460d +size 3664499456 diff --git a/KONI-Llama3.1-8B-20240824.Q4_K_M.gguf b/KONI-Llama3.1-8B-20240824.Q4_K_M.gguf new file mode 100644 index 0000000..0c7fbba --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f185838ec7f61a760896c1f1a529810583d16d2f7bca82315aea4c48e2ec68be +size 4920734464 diff --git a/KONI-Llama3.1-8B-20240824.Q4_K_S.gguf b/KONI-Llama3.1-8B-20240824.Q4_K_S.gguf new file mode 100644 index 0000000..8b45361 --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ba961b1d0f1363d1f8a0000803b4322233014a9d8301d4cc2aa539cf76c9cf1 +size 4692669184 diff --git a/KONI-Llama3.1-8B-20240824.Q5_K_M.gguf b/KONI-Llama3.1-8B-20240824.Q5_K_M.gguf new file mode 100644 index 0000000..edebcba --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31bb6a073cf84be948d6304b8447ac77d304591728d256b0c69da519d2489246 +size 5732987648 diff --git a/KONI-Llama3.1-8B-20240824.Q5_K_S.gguf b/KONI-Llama3.1-8B-20240824.Q5_K_S.gguf new file mode 100644 index 0000000..728dfdf --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c18e5af762d01d909fc5dc724f4ee9d85682216f69854a2bc94c4687004a901 +size 5599294208 diff --git a/KONI-Llama3.1-8B-20240824.Q6_K.gguf b/KONI-Llama3.1-8B-20240824.Q6_K.gguf new file mode 100644 index 0000000..6266382 --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2ee79cc942e6ffb71403c6d616e5f224f19744a344ae8c98f7d38d207667941 +size 6596006656 diff --git a/KONI-Llama3.1-8B-20240824.Q8_0.gguf b/KONI-Llama3.1-8B-20240824.Q8_0.gguf new file mode 100644 index 0000000..0f08591 --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44261fc28e89e51d93e81ed1edc2345bf921d5ca2002376803c05f0340c876a7 +size 8540771072 diff --git a/KONI-Llama3.1-8B-20240824.f16.gguf b/KONI-Llama3.1-8B-20240824.f16.gguf new file mode 100644 index 0000000..0e21080 --- /dev/null +++ b/KONI-Llama3.1-8B-20240824.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7836d10eefa43c0d48172bec41270445ebed976dafefdbff305968cde1022ed7 +size 16068891392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..853d469 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: KISTI-KONI/KONI-Llama3.1-8B-20240824 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/KISTI-KONI/KONI-Llama3.1-8B-20240824 + + +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/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-20240824-GGUF/resolve/main/KONI-Llama3.1-8B-20240824.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. + +