commit 303556c51346c300f3a5009912ab1214575aaa61 Author: ModelHub XC Date: Sun Oct 4 21:15:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2c88c72 --- /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-PortMIS-Ko-8B-Instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-PortMIS-Ko-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_M.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_M.gguf new file mode 100644 index 0000000..72060e0 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:092e3c9d1313516c9c76736c2aab555d44099f44ffb36fab28ed13e0066b5034 +size 3784824352 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_S.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_S.gguf new file mode 100644 index 0000000..df175f6 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a38bc2691c53089bfc855b295f5a1910af1b745ba5bb8c641f600d37db8e29ad +size 3682326048 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_XS.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_XS.gguf new file mode 100644 index 0000000..82fe6d9 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db0cb1ab98334a7c1ae2ba8c330ee42febb0ffb38a91db6aff9f4e5aad92c4b +size 3518748192 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.IQ4_XS.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..5ddd3cd --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463f3df6a160bdcfeace19c0c2238bdb54e2a8b26f96ef9cee31dab257d563aa +size 4484363808 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q2_K.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..066ffd4 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee68ee09bbf7e3cd408551e4ecc83d9a0670c692f1ebb56c95f32c022de3f64f +size 3179132448 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_L.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..8ee9ee0 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ef83ded9d1160d87a582a45228745b843ab3325ac3f7566c446cef3e849e291 +size 4321957408 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_M.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..60300fc --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eeac582fc3f00b514a355e039345accc9aff202177413ed3bd1452a54c21aa1 +size 4018918944 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_S.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..cde66ff --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b007c811c23e3a91f9529cf6f57db4ccbc3387d7195d949b5ac935a85acde7e +size 3664500256 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_M.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..fe27727 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c925dbcff0569f17633cf41c5307b1db75e352f7b75dae6c53f32b14984b469f +size 4920735264 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_S.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..b8e7915 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f28b7f0369f4c066af665bd6abf02d64d0b0ce1cdb4a9ad3aebb08736a342bb4 +size 4692669984 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_M.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..88e122e --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6bdef2617b42b6cb7edee9ea2c6a03aec0c1200597bb7d7f95a11fdca454191 +size 5732988448 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_S.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..8e43119 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba458c12aac94c7d3c78649eb941c636a50ea62e8744c7d37b1c0a672d425684 +size 5599295008 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q6_K.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..8538f3f --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1523e844f5c12e12107a46c18dd35c171fd34c99becd72e8efe63a2fd20ba80d +size 6596007456 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.Q8_0.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..741c0a4 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b062f835a3ba7c07caf7a0e56551e904e94f505ea86ce3dcb6a6c871e351c45 +size 8540771872 diff --git a/Llama-3-PortMIS-Ko-8B-Instruct.f16.gguf b/Llama-3-PortMIS-Ko-8B-Instruct.f16.gguf new file mode 100644 index 0000000..8526735 --- /dev/null +++ b/Llama-3-PortMIS-Ko-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02ab730b7be62e0d94a6466d46b800a582f0b6ae7694c27ffc907c7f01ef1890 +size 16068892192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1d1571e --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Port-Pilot/Llama-3-PortMIS-Ko-8B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/Port-Pilot/Llama-3-PortMIS-Ko-8B-Instruct + + +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-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-PortMIS-Ko-8B-Instruct-GGUF/resolve/main/Llama-3-PortMIS-Ko-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. + +