commit e225554bd90d7ced47b48acb81a86b8a122987de Author: ModelHub XC Date: Tue Jun 16 00:35:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/shisa-v1-llama3-8b.2e5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5b63be7 --- /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 +shisa-v1-llama3-8b.2e5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v1-llama3-8b.2e5.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6664778 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: shisa-ai/shisa-v1-llama3-8b.2e5 +datasets: +- augmxnt/ultra-orca-boros-en-ja-v1 +language: +- ja +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/shisa-ai/shisa-v1-llama3-8b.2e5 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#shisa-v1-llama3-8b.2e5-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-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/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-v1-llama3-8b.2e5-GGUF/resolve/main/shisa-v1-llama3-8b.2e5.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/shisa-v1-llama3-8b.2e5.IQ4_XS.gguf b/shisa-v1-llama3-8b.2e5.IQ4_XS.gguf new file mode 100644 index 0000000..08a5c98 --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82624a4dd7bdced663926ebd20153dc1b29d7d838ee273dff75159b6604f141d +size 4484364064 diff --git a/shisa-v1-llama3-8b.2e5.Q2_K.gguf b/shisa-v1-llama3-8b.2e5.Q2_K.gguf new file mode 100644 index 0000000..ba52ea1 --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd29c0755a1b3a3f5f21fe3dc95196b1fff24f14e97dd84845660a5002ad17fe +size 3179132704 diff --git a/shisa-v1-llama3-8b.2e5.Q3_K_L.gguf b/shisa-v1-llama3-8b.2e5.Q3_K_L.gguf new file mode 100644 index 0000000..fcb1d6b --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3a1cf0a1f9cc122248cc83c870356c2a618fbc2022ba278d6b86a603d92433 +size 4321957664 diff --git a/shisa-v1-llama3-8b.2e5.Q3_K_M.gguf b/shisa-v1-llama3-8b.2e5.Q3_K_M.gguf new file mode 100644 index 0000000..f0cabc1 --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c144f0a3d9ad67d0b530003e1dbe6f42f45ba7132e0dcda2f6c2ac927eb3c27f +size 4018919200 diff --git a/shisa-v1-llama3-8b.2e5.Q3_K_S.gguf b/shisa-v1-llama3-8b.2e5.Q3_K_S.gguf new file mode 100644 index 0000000..62b5057 --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0897676d05b60ff503d02de52ec00396dda6c6a962f732085dbcb1ef49998572 +size 3664500512 diff --git a/shisa-v1-llama3-8b.2e5.Q4_K_M.gguf b/shisa-v1-llama3-8b.2e5.Q4_K_M.gguf new file mode 100644 index 0000000..d6bdf1b --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:515ed54ecf48fd1b3de0b835a66caee91d1a6fef378fa2d8f0af8f92f53f3521 +size 4920735520 diff --git a/shisa-v1-llama3-8b.2e5.Q4_K_S.gguf b/shisa-v1-llama3-8b.2e5.Q4_K_S.gguf new file mode 100644 index 0000000..9c2a26e --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a1a7089f91f8eee02d6b5d49770c5acf16404d064c2cd3e592a9767cc73589 +size 4692670240 diff --git a/shisa-v1-llama3-8b.2e5.Q5_K_M.gguf b/shisa-v1-llama3-8b.2e5.Q5_K_M.gguf new file mode 100644 index 0000000..13ec5d4 --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e039856c260e190825cc964139d65793d8648f0255a81dabe2e14b99d6450b5e +size 5732988704 diff --git a/shisa-v1-llama3-8b.2e5.Q5_K_S.gguf b/shisa-v1-llama3-8b.2e5.Q5_K_S.gguf new file mode 100644 index 0000000..7745492 --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7279205aa710d4073d045e5979343e3d192d699fd1de778dd8312e50da0e61f +size 5599295264 diff --git a/shisa-v1-llama3-8b.2e5.Q6_K.gguf b/shisa-v1-llama3-8b.2e5.Q6_K.gguf new file mode 100644 index 0000000..87fdb43 --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d6c11dab8c5894ff19bda4f63381cba84b47c665d839f3be967278daaa7a11 +size 6596007712 diff --git a/shisa-v1-llama3-8b.2e5.Q8_0.gguf b/shisa-v1-llama3-8b.2e5.Q8_0.gguf new file mode 100644 index 0000000..cbf6a46 --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:214601fd3c1269da8baf39cc1961de001d07bead7fa1cd7a272b468971e3fe03 +size 8540772128 diff --git a/shisa-v1-llama3-8b.2e5.f16.gguf b/shisa-v1-llama3-8b.2e5.f16.gguf new file mode 100644 index 0000000..9f68324 --- /dev/null +++ b/shisa-v1-llama3-8b.2e5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:525e1349eac6700340115747e12304c212041e34b7486721219f8d0574710a32 +size 16068892448