commit 0b0df50acfeb2993acb62813dcd8b98a10ea669f Author: ModelHub XC Date: Tue Oct 6 17:39:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0ae587b --- /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 +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-SISaAI-Ko-merge-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.IQ4_XS.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..13ed2ad --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:708eb1b033f57044bc7d8ccbd6a6cd03709102fb2e3ddb642ab13f980adc3aac +size 4484368704 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q2_K.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..200107d --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29811c77954ff0c8836310968399e117ef073b1d8a9c9ae8d9f3804ef5ee9b4b +size 3179137344 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_L.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..4cca23e --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571b2e1f858eb59e67fac259f41a8bb379bd1e4502e92a8f2b69bc316a5d4edd +size 4321962304 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_M.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..166358e --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d2cc6a09a853b8b1589afca3f495b27fd8d5fd6df028d851fa5be8dd320ba27 +size 4018923840 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_S.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..703c866 --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33be9afedeb1bbce43bb6e3aa55825d371dd0e168ef6f5540aa0714abf66b027 +size 3664505152 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_M.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..de94492 --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b13083210723735c0f0f3795138de667da9590150aa862899508ef3259e99ec4 +size 4920740160 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_S.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..7644b16 --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f39372978acf511cf54326f27d59dfa64c762d8be6388326e3edab686554f753 +size 4692674880 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_M.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..8d1b96b --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33649f41bbaa43ce68597e45428ee97a936773b11ec65a9f7392141cabee3dbc +size 5732993344 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_S.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..99f62ab --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2aaac2b645e941a490043092a33fbf87e02c29821f662564712d9fec11c72b3 +size 5599299904 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q6_K.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..28653cd --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837e6410f56ed04507dd86fef72d541eeba83ed54f889e0b55663f0f06bc4645 +size 6596012352 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q8_0.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..58495c4 --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b59d71dc57c03ecf7b212d316d7214261a040310ac0b85ff64df5a3e1411383 +size 8540776768 diff --git a/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.f16.gguf b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.f16.gguf new file mode 100644 index 0000000..011e167 --- /dev/null +++ b/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80c1eca6d5287c7a1bb1b0de4c11dd3d32a93c3d9ba6ec4514e9eb63e8c4eccb +size 16068897088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1d78c68 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: asiansoul/Llama-3.1-SISaAI-Ko-merge-8B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/asiansoul/Llama-3.1-SISaAI-Ko-merge-8B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-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/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.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. + +