commit eb1cef48f5ae626afdee225e8f2efe74edaca70e Author: ModelHub XC Date: Thu Jun 18 08:14:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..34129c9 --- /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 +llama3-8b-cpt-sealionv2-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-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..4d1b95d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: aisingapore/Llama-SEA-LION-v2-8B-IT +language: +- en +- id +- ta +- th +- vi +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/aisingapore/Llama-SEA-LION-v2-8B-IT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-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/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-instruct-GGUF/resolve/main/llama3-8b-cpt-sealionv2-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/llama3-8b-cpt-sealionv2-instruct.IQ3_M.gguf b/llama3-8b-cpt-sealionv2-instruct.IQ3_M.gguf new file mode 100644 index 0000000..0b47906 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa71d171c5b266831a27fc52e7df929e709460f68e2da2dafe730ea248445f45 +size 3784823904 diff --git a/llama3-8b-cpt-sealionv2-instruct.IQ3_S.gguf b/llama3-8b-cpt-sealionv2-instruct.IQ3_S.gguf new file mode 100644 index 0000000..f43acc3 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b96ed2ac5673ded2f2edafaefdcb9ca1db08133471b945d18552776fd765b2e +size 3682325600 diff --git a/llama3-8b-cpt-sealionv2-instruct.IQ3_XS.gguf b/llama3-8b-cpt-sealionv2-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..13e8f95 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f3873a702901636d4711f02afa9b481aa5e77429a8ee7a2b13c3105244748f +size 3518747744 diff --git a/llama3-8b-cpt-sealionv2-instruct.IQ4_XS.gguf b/llama3-8b-cpt-sealionv2-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..d0600c5 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f796b3fffc39483b26240e98798eaf5cf06bfcd0f122d243bf9f31f365637325 +size 4484363360 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q2_K.gguf b/llama3-8b-cpt-sealionv2-instruct.Q2_K.gguf new file mode 100644 index 0000000..97ff8bb --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83cff029086c9274527ff76502bb9939b3c18966d73708f33b85be8b80c07efd +size 3179132000 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q3_K_L.gguf b/llama3-8b-cpt-sealionv2-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..e1d6587 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f6c5717a87b9f5db09955b8bc1f7e25acc7c36e11c7cf8442774ea2f69da30 +size 4321956960 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q3_K_M.gguf b/llama3-8b-cpt-sealionv2-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e2c1776 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7dd9e134dba51951547b5394895151a753811f54e03bc6110b66e43ee7c2902 +size 4018918496 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q3_K_S.gguf b/llama3-8b-cpt-sealionv2-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..201e00c --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4d7677331575fe72cf3ee997d7dff30de9ce0d08bf3a28fbc088f3fe01e3b7 +size 3664499808 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q4_K_M.gguf b/llama3-8b-cpt-sealionv2-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f0b6a0e --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29eb7b08726394382a8dc0de876306aaef96004d8280927b39436feb18fb5ae7 +size 4920734816 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q4_K_S.gguf b/llama3-8b-cpt-sealionv2-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..65b7e7c --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ecd91106fec4547d702727ea1ee8d833f928497865be6bc7f28f04caffdfe4 +size 4692669536 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q5_K_M.gguf b/llama3-8b-cpt-sealionv2-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..667b9ab --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffa4ed4fda2e84213988d4de06eeca226a112a6becf24e7235e433d2ad34968 +size 5732988000 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q5_K_S.gguf b/llama3-8b-cpt-sealionv2-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..f1966d5 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e81fbbafa0fe6e3a1f7c6b9d146a6ef53af7c3285f4f43a7cc4609b37d2d85e +size 5599294560 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q6_K.gguf b/llama3-8b-cpt-sealionv2-instruct.Q6_K.gguf new file mode 100644 index 0000000..680a820 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef7f14b7e5aab6f94d876b96bdb9248d87df4ac4a9c45153a45c4d05cefb08c +size 6596007008 diff --git a/llama3-8b-cpt-sealionv2-instruct.Q8_0.gguf b/llama3-8b-cpt-sealionv2-instruct.Q8_0.gguf new file mode 100644 index 0000000..8f091f5 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dbeebb3aac7c71bf333f550e4063ba4dd0ff252e35c23a81d520549a9954b7f +size 8540771424 diff --git a/llama3-8b-cpt-sealionv2-instruct.f16.gguf b/llama3-8b-cpt-sealionv2-instruct.f16.gguf new file mode 100644 index 0000000..79cb7b0 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0609d8195bc1bb7525fcd957ff8f1101cfaf3dcdbc7e34cdbe3c28a2c4328665 +size 16068891744