commit 4e796d4ad277ef52b161fa5c341ac1f1a332b13e Author: ModelHub XC Date: Thu Jun 18 05:14:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-youko-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..62c1c8b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-youko-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..942b862 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: rinna/llama-3-youko-8b +datasets: +- mc4 +- wikipedia +- EleutherAI/pile +- oscar-corpus/colossal-oscar-1.0 +- cc100 +language: +- ja +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- llama +- llama-3 +--- +## About + + + + + +static quants of https://huggingface.co/rinna/llama-3-youko-8b + + +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-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-GGUF/resolve/main/llama-3-youko-8b.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. + + diff --git a/llama-3-youko-8b.IQ3_M.gguf b/llama-3-youko-8b.IQ3_M.gguf new file mode 100644 index 0000000..69386dd --- /dev/null +++ b/llama-3-youko-8b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950c8018ca9d1bce5067c540442af2ea0c2bf43e1b35a2aa4ac9a3e6f55896f4 +size 3784823072 diff --git a/llama-3-youko-8b.IQ3_S.gguf b/llama-3-youko-8b.IQ3_S.gguf new file mode 100644 index 0000000..be4fbce --- /dev/null +++ b/llama-3-youko-8b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4782ebca5b0c75598cc52cd7225eed818f7536980edcbae2efae1d58175f1621 +size 3682324768 diff --git a/llama-3-youko-8b.IQ3_XS.gguf b/llama-3-youko-8b.IQ3_XS.gguf new file mode 100644 index 0000000..1c3fb3a --- /dev/null +++ b/llama-3-youko-8b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7b7a3e3a05b3b8679e3daaa2509c64d95d510a6683f468c42f3190f00005291 +size 3518746912 diff --git a/llama-3-youko-8b.IQ4_XS.gguf b/llama-3-youko-8b.IQ4_XS.gguf new file mode 100644 index 0000000..89278d2 --- /dev/null +++ b/llama-3-youko-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ed3d7ea13c185aa52f1fc35df68d976ce8b34bb2ddebf4c68826eca5fa70a00 +size 4484362528 diff --git a/llama-3-youko-8b.Q2_K.gguf b/llama-3-youko-8b.Q2_K.gguf new file mode 100644 index 0000000..fcea1f9 --- /dev/null +++ b/llama-3-youko-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:563204eed3cbc65c7dbd18f64849a1c3420b3fec49b98a386fe0d209becf5fb1 +size 3179131168 diff --git a/llama-3-youko-8b.Q3_K_L.gguf b/llama-3-youko-8b.Q3_K_L.gguf new file mode 100644 index 0000000..1962876 --- /dev/null +++ b/llama-3-youko-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73252f85ec9a57b227699a6f35b4ad01e10bd8ed5935d8e0a0b3735737c3d0d7 +size 4321956128 diff --git a/llama-3-youko-8b.Q3_K_M.gguf b/llama-3-youko-8b.Q3_K_M.gguf new file mode 100644 index 0000000..5935577 --- /dev/null +++ b/llama-3-youko-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab29c2006f80c903887e70c847d3f6bc03c815dbd797b327f7c5c3f6d3b07692 +size 4018917664 diff --git a/llama-3-youko-8b.Q3_K_S.gguf b/llama-3-youko-8b.Q3_K_S.gguf new file mode 100644 index 0000000..da644d7 --- /dev/null +++ b/llama-3-youko-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbc1d04c13d6ebff543e2705c3b07796dc386a33d3e24623914b4771548aa8fd +size 3664498976 diff --git a/llama-3-youko-8b.Q4_K_M.gguf b/llama-3-youko-8b.Q4_K_M.gguf new file mode 100644 index 0000000..604845f --- /dev/null +++ b/llama-3-youko-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a1d3258f6eaf22ca5363d3c491397cef784723533a5cf15df871132b6bafa23 +size 4920733984 diff --git a/llama-3-youko-8b.Q4_K_S.gguf b/llama-3-youko-8b.Q4_K_S.gguf new file mode 100644 index 0000000..bba27a8 --- /dev/null +++ b/llama-3-youko-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c7e7eced2fc92312b28ef389f3ed584429df764ecb1be739810f82caf0c2ca5 +size 4692668704 diff --git a/llama-3-youko-8b.Q5_K_M.gguf b/llama-3-youko-8b.Q5_K_M.gguf new file mode 100644 index 0000000..9119d3a --- /dev/null +++ b/llama-3-youko-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf1408312efee17f6f676281b16958b29f441aeabcecbffbbdbeb0f9c9e1992 +size 5732987168 diff --git a/llama-3-youko-8b.Q5_K_S.gguf b/llama-3-youko-8b.Q5_K_S.gguf new file mode 100644 index 0000000..5e4f91f --- /dev/null +++ b/llama-3-youko-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:437df6a37b0801310d0338e4f78213f69e3c5c8845d8e456e459016bf29a62a6 +size 5599293728 diff --git a/llama-3-youko-8b.Q6_K.gguf b/llama-3-youko-8b.Q6_K.gguf new file mode 100644 index 0000000..8aa9ff5 --- /dev/null +++ b/llama-3-youko-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7cbdc0b5a05e344631e4c75099cdc98034377c0d6f2089a1c388e8f38ea521c +size 6596006176 diff --git a/llama-3-youko-8b.Q8_0.gguf b/llama-3-youko-8b.Q8_0.gguf new file mode 100644 index 0000000..02158e2 --- /dev/null +++ b/llama-3-youko-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d91bd301d632580be1459c411043dfa7b4d9ac5883f82d4f1f345dd95237d803 +size 8540770592 diff --git a/llama-3-youko-8b.f16.gguf b/llama-3-youko-8b.f16.gguf new file mode 100644 index 0000000..01160bd --- /dev/null +++ b/llama-3-youko-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68fc3739988612d462c2d62cb876b1545dfb86a12035ec97d36091883b68ccd9 +size 16068890912