commit 6d6c542f15fc03584e42a574ce5dd3701fd20c6c Author: ModelHub XC Date: Thu Jun 25 18:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-SEA-LION-v3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..065b3ab --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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-SEA-LION-v3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-SEA-LION-v3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-SEA-LION-v3-8B.IQ4_XS.gguf b/Llama-SEA-LION-v3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..f6feab1 --- /dev/null +++ b/Llama-SEA-LION-v3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ab226167cbf00d50a5ebac270ecc76e1b9d3b2fa4b66f82226871b63117f4a +size 4484363456 diff --git a/Llama-SEA-LION-v3-8B.Q2_K.gguf b/Llama-SEA-LION-v3-8B.Q2_K.gguf new file mode 100644 index 0000000..db5cd3d --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1493df8ee7b0147cae4d7bc0ef2a4695f47b8b81e329f97365e64a7901557be9 +size 3179132096 diff --git a/Llama-SEA-LION-v3-8B.Q3_K_L.gguf b/Llama-SEA-LION-v3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..c137bed --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2088d319a98a420b84279e6644001432e9f666baa7d58ba6915cceed64ec7772 +size 4321957056 diff --git a/Llama-SEA-LION-v3-8B.Q3_K_M.gguf b/Llama-SEA-LION-v3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..9180b77 --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d69e41120e5fa2c6c1b1acd8f645fb27091552ff53cabc566903397d8c4cbd +size 4018918592 diff --git a/Llama-SEA-LION-v3-8B.Q3_K_S.gguf b/Llama-SEA-LION-v3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..9e73253 --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5619a3c96fa06ec3b5f8db73370ddfc698e26d7a52c8e18c1fcb527c60ce0be0 +size 3664499904 diff --git a/Llama-SEA-LION-v3-8B.Q4_K_M.gguf b/Llama-SEA-LION-v3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..b34edcc --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87afe0f4878a3c066a6979bb0b17e6215a0f8590cfb4866fcc470a702b6a4f7 +size 4920734912 diff --git a/Llama-SEA-LION-v3-8B.Q4_K_S.gguf b/Llama-SEA-LION-v3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..fef785b --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250580dab26a90c69d1c1cd3cf7b7c3623430869eb7d9fcdd21eb362fed98e04 +size 4692669632 diff --git a/Llama-SEA-LION-v3-8B.Q5_K_M.gguf b/Llama-SEA-LION-v3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..fc7e6bc --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a28d723e7e6dccf42088bda93a02478d413a11a511c107664f290209515485eb +size 5732988096 diff --git a/Llama-SEA-LION-v3-8B.Q5_K_S.gguf b/Llama-SEA-LION-v3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..3dfb486 --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65dcaa3a583f07a38a633ec696f27904c910de16e6ebdc5cebf7a5abb81f50c8 +size 5599294656 diff --git a/Llama-SEA-LION-v3-8B.Q6_K.gguf b/Llama-SEA-LION-v3-8B.Q6_K.gguf new file mode 100644 index 0000000..c6af268 --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289bb1dda453dc2a803ef93adfa25f00701658d3cccb3da1b4db9cd1c2eeedb8 +size 6596007104 diff --git a/Llama-SEA-LION-v3-8B.Q8_0.gguf b/Llama-SEA-LION-v3-8B.Q8_0.gguf new file mode 100644 index 0000000..adcaa88 --- /dev/null +++ b/Llama-SEA-LION-v3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074c8850f83be45900f63aa3e99e6c31d6f2eac6754533c2a69b296d04e6400e +size 8540771520 diff --git a/Llama-SEA-LION-v3-8B.f16.gguf b/Llama-SEA-LION-v3-8B.f16.gguf new file mode 100644 index 0000000..0ca05b6 --- /dev/null +++ b/Llama-SEA-LION-v3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91956ce6115a77967e16163779f55680889bb052d79cfd80a24586fef8e02dce +size 16068891840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c5670c9 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: aisingapore/Llama-SEA-LION-v3-8B +language: +- en +- zh +- vi +- id +- th +- fil +- ta +- ms +- km +- lo +- my +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/aisingapore/Llama-SEA-LION-v3-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-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-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-SEA-LION-v3-8B-GGUF/resolve/main/Llama-SEA-LION-v3-8B.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. + +