commit 7803cca386d90ec8eecaa6badd3b49e5b3ae1e03 Author: ModelHub XC Date: Thu Jun 18 04:54:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-youko-8b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21e7b4a --- /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-instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-youko-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..64d7084 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: rinna/llama-3-youko-8b-instruct +datasets: +- CohereForAI/aya_dataset +- kunishou/databricks-dolly-15k-ja +- kunishou/HelpSteer-35k-ja +- kunishou/HelpSteer2-20k-ja +- kunishou/hh-rlhf-49k-ja +- kunishou/oasst1-chat-44k-ja +- kunishou/oasst2-chat-68k-ja +- meta-math/MetaMathQA +- OpenAssistant/oasst1 +- OpenAssistant/oasst2 +- sahil2801/CodeAlpaca-20k +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-instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-youko-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-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-8b-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-youko-8b-instruct-GGUF/resolve/main/llama-3-youko-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. + + diff --git a/llama-3-youko-8b-instruct.IQ3_M.gguf b/llama-3-youko-8b-instruct.IQ3_M.gguf new file mode 100644 index 0000000..3372900 --- /dev/null +++ b/llama-3-youko-8b-instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e425a5862d843c37439cb36fbfe8700aa0c628fbb6e6a4ea4dd6f61cfb69fac5 +size 3784824512 diff --git a/llama-3-youko-8b-instruct.IQ3_S.gguf b/llama-3-youko-8b-instruct.IQ3_S.gguf new file mode 100644 index 0000000..765bc5c --- /dev/null +++ b/llama-3-youko-8b-instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:326dde91b6394cf241583894b8abc72aada6e992ce149a02ae291243bca87b78 +size 3682326208 diff --git a/llama-3-youko-8b-instruct.IQ3_XS.gguf b/llama-3-youko-8b-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..6369561 --- /dev/null +++ b/llama-3-youko-8b-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f375cb0acc391f821d194ed59bfd62cf8a0b614b1b884a9ff3f75bfe1e4a0940 +size 3518748352 diff --git a/llama-3-youko-8b-instruct.IQ4_XS.gguf b/llama-3-youko-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..7e00d88 --- /dev/null +++ b/llama-3-youko-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aa5786965a2051db0d56b608a2d9ebea791c4a15b92ed4ae5ac539a826ff52b +size 4484363968 diff --git a/llama-3-youko-8b-instruct.Q2_K.gguf b/llama-3-youko-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..b2264df --- /dev/null +++ b/llama-3-youko-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907c959bff74179a57c4eec6f03f2d9ac81de6c4c02b7246ce1452191f599c0f +size 3179132608 diff --git a/llama-3-youko-8b-instruct.Q3_K_L.gguf b/llama-3-youko-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..b350cb2 --- /dev/null +++ b/llama-3-youko-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb8afafd4e4d550c0b9b86337c3ea8c6d68d9bc1a79dbbb86f16e07f939f3fed +size 4321957568 diff --git a/llama-3-youko-8b-instruct.Q3_K_M.gguf b/llama-3-youko-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..92c706b --- /dev/null +++ b/llama-3-youko-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ebad921382ae7371cf55663113215927de69c9a64ca4f9cb5ef44aa63943f33 +size 4018919104 diff --git a/llama-3-youko-8b-instruct.Q3_K_S.gguf b/llama-3-youko-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..72b1d84 --- /dev/null +++ b/llama-3-youko-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9186f866044aeae57b76797ec1819c7d254f9c051c2f2a3df4a4c1bc5017097b +size 3664500416 diff --git a/llama-3-youko-8b-instruct.Q4_K_M.gguf b/llama-3-youko-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..7f02a4a --- /dev/null +++ b/llama-3-youko-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:675dcc00881e7a8d3da8485258fa7d2a18400bf0fc29c69f303c7675e8bb2041 +size 4920735424 diff --git a/llama-3-youko-8b-instruct.Q4_K_S.gguf b/llama-3-youko-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..65ac0e2 --- /dev/null +++ b/llama-3-youko-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:891e74d6d197f01ed3906504c7539c8a8cb7460db4c0dde5321be53c62abb112 +size 4692670144 diff --git a/llama-3-youko-8b-instruct.Q5_K_M.gguf b/llama-3-youko-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..8bfff41 --- /dev/null +++ b/llama-3-youko-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373111b7038f0e0ea02d13a2b2f0334db0efc116e73b820fb75c21cbf043f53e +size 5732988608 diff --git a/llama-3-youko-8b-instruct.Q5_K_S.gguf b/llama-3-youko-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..351d345 --- /dev/null +++ b/llama-3-youko-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e454bd9da2ad028531ce136960696587e0b12296453c2956567b2285454a6c +size 5599295168 diff --git a/llama-3-youko-8b-instruct.Q6_K.gguf b/llama-3-youko-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..08c4a53 --- /dev/null +++ b/llama-3-youko-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2e076d0e4f874e7e86bf8b4500b3c8da96b13ab1f3999ef84f94a50d1f13e8 +size 6596007616 diff --git a/llama-3-youko-8b-instruct.Q8_0.gguf b/llama-3-youko-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..07c8d42 --- /dev/null +++ b/llama-3-youko-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc004ee290b6f763c4027c64e4e58c0bfe6fdd648ba66331554721aad127269 +size 8540772032 diff --git a/llama-3-youko-8b-instruct.f16.gguf b/llama-3-youko-8b-instruct.f16.gguf new file mode 100644 index 0000000..71a4664 --- /dev/null +++ b/llama-3-youko-8b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a1e07695b74d0f641ac1e0115febeb3eb45f51fcc18d95ea39c082c9168bf50 +size 16068892352