commit ddf29b09cf81a9b603a0ed22db9bbcfcc3003a4c Author: ModelHub XC Date: Sat Oct 17 04:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..48dc141 --- /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-R-20250831.f16.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-R-20250831.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KONI-Llama3.1-8B-R-20250831.IQ4_XS.gguf b/KONI-Llama3.1-8B-R-20250831.IQ4_XS.gguf new file mode 100644 index 0000000..c05d406 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63bab4696a1fc9e6ed39fff83a8860994dfcead709413136053b664a0bf3450a +size 4484369120 diff --git a/KONI-Llama3.1-8B-R-20250831.Q2_K.gguf b/KONI-Llama3.1-8B-R-20250831.Q2_K.gguf new file mode 100644 index 0000000..e707a9c --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5184fa53d868713790d44bd7334988ff4fde129b47b23a5c0f90d98d6720d64d +size 3179137760 diff --git a/KONI-Llama3.1-8B-R-20250831.Q3_K_L.gguf b/KONI-Llama3.1-8B-R-20250831.Q3_K_L.gguf new file mode 100644 index 0000000..cf514ff --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db5596d1a64f4287f7f82dbfb738c4337124db72739e3d0787f1a7feee3f0652 +size 4321962720 diff --git a/KONI-Llama3.1-8B-R-20250831.Q3_K_M.gguf b/KONI-Llama3.1-8B-R-20250831.Q3_K_M.gguf new file mode 100644 index 0000000..8a15e00 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:704ecf925314a795d454ae68f7f52b8db2a61a819abf9bb06332f0a9543b4a5b +size 4018924256 diff --git a/KONI-Llama3.1-8B-R-20250831.Q3_K_S.gguf b/KONI-Llama3.1-8B-R-20250831.Q3_K_S.gguf new file mode 100644 index 0000000..6a5350a --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccad407991229824941daf6ddee2d3294ebcdfb70a1136988cb69d7461538a54 +size 3664505568 diff --git a/KONI-Llama3.1-8B-R-20250831.Q4_K_M.gguf b/KONI-Llama3.1-8B-R-20250831.Q4_K_M.gguf new file mode 100644 index 0000000..2f7aedc --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f66206ba6b1b6f352cd06e08a3d97ec4bf4def79efd473ed41b926fbe13fbd +size 4920740576 diff --git a/KONI-Llama3.1-8B-R-20250831.Q4_K_S.gguf b/KONI-Llama3.1-8B-R-20250831.Q4_K_S.gguf new file mode 100644 index 0000000..0fb651f --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e267603f682334be345f6d85be251577d9731d474040da1d46416418f315b31 +size 4692675296 diff --git a/KONI-Llama3.1-8B-R-20250831.Q5_K_M.gguf b/KONI-Llama3.1-8B-R-20250831.Q5_K_M.gguf new file mode 100644 index 0000000..c42cc9e --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c31cbe05739bc59beea8c9d5b91a1d0cc7713a9474f4c6c2d70595a30585aa0e +size 5732993760 diff --git a/KONI-Llama3.1-8B-R-20250831.Q5_K_S.gguf b/KONI-Llama3.1-8B-R-20250831.Q5_K_S.gguf new file mode 100644 index 0000000..cfd8d9c --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e965632d1fefbc2a6aa7989ac3b8a6cecb01436b75432e6d7411ac11044b1d +size 5599300320 diff --git a/KONI-Llama3.1-8B-R-20250831.Q6_K.gguf b/KONI-Llama3.1-8B-R-20250831.Q6_K.gguf new file mode 100644 index 0000000..4ea10f3 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b7e82efc80f273175214d5e1cb1f51701b5cb00eaacb1b24cb055fb3ee22ad9 +size 6596012768 diff --git a/KONI-Llama3.1-8B-R-20250831.Q8_0.gguf b/KONI-Llama3.1-8B-R-20250831.Q8_0.gguf new file mode 100644 index 0000000..e95cf54 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6882c6a880d8fc8cce9a3f9a58bbf2fa2a4ddb3f8e570e955a1cbf3040626756 +size 8540777184 diff --git a/KONI-Llama3.1-8B-R-20250831.f16.gguf b/KONI-Llama3.1-8B-R-20250831.f16.gguf new file mode 100644 index 0000000..6046bb6 --- /dev/null +++ b/KONI-Llama3.1-8B-R-20250831.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf493db3f766463e540e18279f9abfd4080b0820a84d02ac93a36d413fb794e +size 16068897504 diff --git a/README.md b/README.md new file mode 100644 index 0000000..564ec2a --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: KISTI-KONI/KONI-Llama3.1-8B-R-20250831 +language: +- ko +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- pytorch +- llama3.1 +- KISTI +- KONI +- 8b +--- +## About + + + + + + + + + +static quants of https://huggingface.co/KISTI-KONI/KONI-Llama3.1-8B-R-20250831 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KONI-Llama3.1-8B-R-20250831-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-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/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-R-20250831-GGUF/resolve/main/KONI-Llama3.1-8B-R-20250831.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. + +