commit bdcbee90feed70cf7d2fbfa4b3a73df3b3d4f67b Author: ModelHub XC Date: Tue Jun 30 11:19:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..904f606 --- /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-Instruct-20250217.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.f16.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KONI-Llama3.1-8B-Instruct-20250217.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KONI-Llama3.1-8B-Instruct-20250217.IQ4_XS.gguf b/KONI-Llama3.1-8B-Instruct-20250217.IQ4_XS.gguf new file mode 100644 index 0000000..87ee0fe --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf1e46fe21f7297ee1f785af0dd57fb16ecc1f8a090840ccaaf1e2d7fa42691 +size 4484368384 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q2_K.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q2_K.gguf new file mode 100644 index 0000000..99d764d --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4acf5ff4698df01400237a6b04df736e1b1c8c98a804313a329f7bc6cb7ade50 +size 3179137024 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_L.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_L.gguf new file mode 100644 index 0000000..9c9f1ab --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc08e71500a8152d2d30d6db005d21e2f96581071315ea115efe9a2558f77cf +size 4321961984 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_M.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_M.gguf new file mode 100644 index 0000000..2d1da13 --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232060527a95cd795e93d3c8938dc0898fea3c63945a569d077957ba9872c471 +size 4018923520 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_S.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_S.gguf new file mode 100644 index 0000000..1c01b3b --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cfbe41b771297f3a7e5a82ceba5ef5b255489882bc5d3331d48448bf658d7a1 +size 3664504832 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q4_K_M.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q4_K_M.gguf new file mode 100644 index 0000000..b4dc709 --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb41ea069752cfb17e9d4f77e7285857079838eb6e55246490978a05df890bea +size 4920739840 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q4_K_S.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q4_K_S.gguf new file mode 100644 index 0000000..c14707e --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5156d3b13e7ed765c8fcd742a646785b18675bf185fbe99902ac7a7ef74c2dc +size 4692674560 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q5_K_M.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q5_K_M.gguf new file mode 100644 index 0000000..732a00e --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7b6080fb3377ec358e62e6743df1cbba60c413168fcb767cf29539d342968e +size 5732993024 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q5_K_S.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q5_K_S.gguf new file mode 100644 index 0000000..07cc221 --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a01c860c4abb2d6d792edb0a7330be96b2ff9bc488073a541ef1ecc105f20f +size 5599299584 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q6_K.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q6_K.gguf new file mode 100644 index 0000000..52533c9 --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9900984fb93a0f5d9420004a42e4e5b35525061ff54cc148681adf870a420d +size 6596012032 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.Q8_0.gguf b/KONI-Llama3.1-8B-Instruct-20250217.Q8_0.gguf new file mode 100644 index 0000000..9b73917 --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54658c16846baa904e5be14085242cbc90ccea5ed46a55bc911bcd1454aefcf0 +size 8540776448 diff --git a/KONI-Llama3.1-8B-Instruct-20250217.f16.gguf b/KONI-Llama3.1-8B-Instruct-20250217.f16.gguf new file mode 100644 index 0000000..8f9d95f --- /dev/null +++ b/KONI-Llama3.1-8B-Instruct-20250217.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eeb05e10bd5c25daa20ef0d8024bf953640a68b0fcd866b87c13f6f62024b4a +size 16068896768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7b91225 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: KONIexp/KONI-Llama3.1-8B-Instruct-cdj2-20250217 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/KONIexp/KONI-Llama3.1-8B-Instruct-cdj2-20250217 + + +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-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KONI-Llama3.1-8B-Instruct-20250217-GGUF/resolve/main/KONI-Llama3.1-8B-Instruct-20250217.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. + +