commit d7c07ed4a62bd4d468293ad6f2a7c7de9a8e0db7 Author: ModelHub XC Date: Sat May 9 06:43:49 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f9d661e --- /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-KoEn-8B-magic8.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-KoEn-8B-magic8.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-KoEn-8B-magic8.IQ4_XS.gguf b/Llama-3.1-KoEn-8B-magic8.IQ4_XS.gguf new file mode 100644 index 0000000..9661973 --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212026d86ce81f6503879318c4f4ce5953e3b73e34ee28e01f31da07a93fbe99 +size 4484368448 diff --git a/Llama-3.1-KoEn-8B-magic8.Q2_K.gguf b/Llama-3.1-KoEn-8B-magic8.Q2_K.gguf new file mode 100644 index 0000000..8d112c2 --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ce155b0db5797a7918f1ab8dccac5a9f5ec7cc2ad8c4fdb33d43b7160f8bce +size 3179137088 diff --git a/Llama-3.1-KoEn-8B-magic8.Q3_K_L.gguf b/Llama-3.1-KoEn-8B-magic8.Q3_K_L.gguf new file mode 100644 index 0000000..50c71cd --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:711efdda83605ddcc5ba9bbff3f75da2b155f8224ed463f92150a5e2abac4240 +size 4321962048 diff --git a/Llama-3.1-KoEn-8B-magic8.Q3_K_M.gguf b/Llama-3.1-KoEn-8B-magic8.Q3_K_M.gguf new file mode 100644 index 0000000..b960910 --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fafe96481e36e78f7144a9b357499d2067f8945aadb1e2388ab2ebed89a16bc +size 4018923584 diff --git a/Llama-3.1-KoEn-8B-magic8.Q3_K_S.gguf b/Llama-3.1-KoEn-8B-magic8.Q3_K_S.gguf new file mode 100644 index 0000000..924641c --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7953bd94a63c551c13c44878bbc0f047de40e4398d735b45029eb148b1bacaa9 +size 3664504896 diff --git a/Llama-3.1-KoEn-8B-magic8.Q4_K_M.gguf b/Llama-3.1-KoEn-8B-magic8.Q4_K_M.gguf new file mode 100644 index 0000000..f821cd8 --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332260394801f0bfa97b2396f34aadc4e46e9addf744e4b610a58eb16b824a4c +size 4920739904 diff --git a/Llama-3.1-KoEn-8B-magic8.Q4_K_S.gguf b/Llama-3.1-KoEn-8B-magic8.Q4_K_S.gguf new file mode 100644 index 0000000..66f0911 --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f74e51d55490194b108d5b036b529026d074b18d0bcc3ea595618c207706c3c3 +size 4692674624 diff --git a/Llama-3.1-KoEn-8B-magic8.Q5_K_M.gguf b/Llama-3.1-KoEn-8B-magic8.Q5_K_M.gguf new file mode 100644 index 0000000..53c9ded --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f4dee225a14b07672df221288844e762212fd34779861e8ca14984bccf466f2 +size 5732993088 diff --git a/Llama-3.1-KoEn-8B-magic8.Q5_K_S.gguf b/Llama-3.1-KoEn-8B-magic8.Q5_K_S.gguf new file mode 100644 index 0000000..e6dae1c --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df47119f597dfa31ea4eda29cbe073c1c644828ca0371aa744a2613b8df3595 +size 5599299648 diff --git a/Llama-3.1-KoEn-8B-magic8.Q6_K.gguf b/Llama-3.1-KoEn-8B-magic8.Q6_K.gguf new file mode 100644 index 0000000..192de31 --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50267ad43da2459c92b811613fbf0ee46e2ec5da0d9cf7d8dc10889d80bddd77 +size 6596012096 diff --git a/Llama-3.1-KoEn-8B-magic8.Q8_0.gguf b/Llama-3.1-KoEn-8B-magic8.Q8_0.gguf new file mode 100644 index 0000000..cfbe653 --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a488dd6c5c2fce07c8e28e2cea76e51d8cc97e07ae61e1bca6b0d349df52e49 +size 8540776512 diff --git a/Llama-3.1-KoEn-8B-magic8.f16.gguf b/Llama-3.1-KoEn-8B-magic8.f16.gguf new file mode 100644 index 0000000..46b5281 --- /dev/null +++ b/Llama-3.1-KoEn-8B-magic8.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aa3d2ca45a12b65c35db33351c5ee87ea043f3dc714f07d4a7705828fcb16b9 +size 16068896832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c9cec42 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: muzerai/Llama-3.1-KoEn-8B-magic8 +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/muzerai/Llama-3.1-KoEn-8B-magic8 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-KoEn-8B-magic8-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/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-KoEn-8B-magic8-GGUF/resolve/main/Llama-3.1-KoEn-8B-magic8.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. + +