commit ea20e1bb5c7af46751c73ad8a0329cbd00307265 Author: ModelHub XC Date: Wed Jul 1 19:57:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-suzume_liner0.8-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..942c29b --- /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-3-8B-suzume_liner0.8.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-suzume_liner0.8.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-suzume_liner0.8.IQ4_XS.gguf b/Llama-3-8B-suzume_liner0.8.IQ4_XS.gguf new file mode 100644 index 0000000..4651884 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a36c033c286ffe938a404dc05fe43188a669698162b7649ba2790961c90e0a +size 4484363936 diff --git a/Llama-3-8B-suzume_liner0.8.Q2_K.gguf b/Llama-3-8B-suzume_liner0.8.Q2_K.gguf new file mode 100644 index 0000000..8d45a7f --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:683e85843e265524df05410cb759002e3b6c17738b5a6eb24692021bd47420e2 +size 3179132576 diff --git a/Llama-3-8B-suzume_liner0.8.Q3_K_L.gguf b/Llama-3-8B-suzume_liner0.8.Q3_K_L.gguf new file mode 100644 index 0000000..b06f8eb --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f657e78d25e1ebf294c4c3d06459cb5fff83b9ba874a76d79bc52c41229554d +size 4321957536 diff --git a/Llama-3-8B-suzume_liner0.8.Q3_K_M.gguf b/Llama-3-8B-suzume_liner0.8.Q3_K_M.gguf new file mode 100644 index 0000000..85362a1 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2e782bc43630c2d69e6a492ff0cd94eb68fb69561f7497b6e7902a683b758cd +size 4018919072 diff --git a/Llama-3-8B-suzume_liner0.8.Q3_K_S.gguf b/Llama-3-8B-suzume_liner0.8.Q3_K_S.gguf new file mode 100644 index 0000000..2cbdca0 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc2bc07f90e664b307bf457cf5194e54b12359f2d392910f1d04d14c01e99c18 +size 3664500384 diff --git a/Llama-3-8B-suzume_liner0.8.Q4_K_M.gguf b/Llama-3-8B-suzume_liner0.8.Q4_K_M.gguf new file mode 100644 index 0000000..67dbed5 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e60fc7b7f3ec0d9c5b00d467d51165bb98775a42b0cd6d5ab5f89787372c1ec0 +size 4920735392 diff --git a/Llama-3-8B-suzume_liner0.8.Q4_K_S.gguf b/Llama-3-8B-suzume_liner0.8.Q4_K_S.gguf new file mode 100644 index 0000000..c40277d --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f3273087c7525ed3cd163e5fb23467120b72bfd5aa6deb888f242e22577db85 +size 4692670112 diff --git a/Llama-3-8B-suzume_liner0.8.Q5_K_M.gguf b/Llama-3-8B-suzume_liner0.8.Q5_K_M.gguf new file mode 100644 index 0000000..0944d5a --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0222498d46ef5022ba8e67b7b29a35803597b119f964fc3f7aa51b0562395821 +size 5732988576 diff --git a/Llama-3-8B-suzume_liner0.8.Q5_K_S.gguf b/Llama-3-8B-suzume_liner0.8.Q5_K_S.gguf new file mode 100644 index 0000000..352b31e --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8619d71e419257f410524f98ea4452e35ac9048c00e3099fa9ff612ba09174b8 +size 5599295136 diff --git a/Llama-3-8B-suzume_liner0.8.Q6_K.gguf b/Llama-3-8B-suzume_liner0.8.Q6_K.gguf new file mode 100644 index 0000000..e733274 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f13757624eb6b8a358ef50e66c74582373ceb23b4228a7303aa81d22139df82 +size 6596007584 diff --git a/Llama-3-8B-suzume_liner0.8.Q8_0.gguf b/Llama-3-8B-suzume_liner0.8.Q8_0.gguf new file mode 100644 index 0000000..abfc7a8 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9fafab634e83e652a92892cc514a8cc78bcda91e0637dd7e27c89bdc66140bb +size 8540772000 diff --git a/Llama-3-8B-suzume_liner0.8.f16.gguf b/Llama-3-8B-suzume_liner0.8.f16.gguf new file mode 100644 index 0000000..ce52541 --- /dev/null +++ b/Llama-3-8B-suzume_liner0.8.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44747dc27132d3cc3c2cfaaee29ca3eacb0584f73714efe3018edd004a6fbb9 +size 16068892320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d1aafbd --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: noirchan/Llama-3-8B-suzume_liner0.8 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/noirchan/Llama-3-8B-suzume_liner0.8 + + +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-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-suzume_liner0.8-GGUF/resolve/main/Llama-3-8B-suzume_liner0.8.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. + +