commit 748d6496f35269d53bacddc1c0f437c3aa6b1ff0 Author: ModelHub XC Date: Thu Jun 18 08:34:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-cpt-sealionv2-base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..00d2193 --- /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-base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sealionv2-base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..951f9de --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: aisingapore/Llama-SEA-LION-v2-8B +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 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-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-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sealionv2-base-GGUF/resolve/main/llama3-8b-cpt-sealionv2-base.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-base.IQ3_M.gguf b/llama3-8b-cpt-sealionv2-base.IQ3_M.gguf new file mode 100644 index 0000000..003d635 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b8a32779704cf88a0b1325b1497a010236f0297bd6ff9e9b1992ab61fe97e24 +size 3784823424 diff --git a/llama3-8b-cpt-sealionv2-base.IQ3_S.gguf b/llama3-8b-cpt-sealionv2-base.IQ3_S.gguf new file mode 100644 index 0000000..c0babc8 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba166bdf87ee1c2e90b8a8cf2c48cb2cb280d21aa48d737f1415ddd9ca8b6852 +size 3682325120 diff --git a/llama3-8b-cpt-sealionv2-base.IQ3_XS.gguf b/llama3-8b-cpt-sealionv2-base.IQ3_XS.gguf new file mode 100644 index 0000000..0456392 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8fe281abc2ec759e8e3a8e5612f3fc02b899ea1c33616cb8932531b7d2a6541 +size 3518747264 diff --git a/llama3-8b-cpt-sealionv2-base.IQ4_XS.gguf b/llama3-8b-cpt-sealionv2-base.IQ4_XS.gguf new file mode 100644 index 0000000..92dffb7 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e8e038f4168d16c8bbb8c7cabc1d3dfa662546d4ac1e9b7c7f50c39817b48b +size 4484362880 diff --git a/llama3-8b-cpt-sealionv2-base.Q2_K.gguf b/llama3-8b-cpt-sealionv2-base.Q2_K.gguf new file mode 100644 index 0000000..463efb3 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77e49df90ab7b80deb8bffb38694cfb1a10fb524e403c1998540db2bb28fc859 +size 3179131520 diff --git a/llama3-8b-cpt-sealionv2-base.Q3_K_L.gguf b/llama3-8b-cpt-sealionv2-base.Q3_K_L.gguf new file mode 100644 index 0000000..00d418c --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372752c1cf8403c884105252246be9b39b013cd1531e1d8a81b2a756dc528fd4 +size 4321956480 diff --git a/llama3-8b-cpt-sealionv2-base.Q3_K_M.gguf b/llama3-8b-cpt-sealionv2-base.Q3_K_M.gguf new file mode 100644 index 0000000..c1c51d4 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342ef2623d2d8ea26b1e11713566171457c10befd64fbf672498fba6ca97126a +size 4018918016 diff --git a/llama3-8b-cpt-sealionv2-base.Q3_K_S.gguf b/llama3-8b-cpt-sealionv2-base.Q3_K_S.gguf new file mode 100644 index 0000000..6f83e05 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ceb17ab09f9917285275f4f27321194941a1bed0f41ed470c503ff4948f665 +size 3664499328 diff --git a/llama3-8b-cpt-sealionv2-base.Q4_K_M.gguf b/llama3-8b-cpt-sealionv2-base.Q4_K_M.gguf new file mode 100644 index 0000000..d71dc4e --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4766acf8a97722538c81a8d36400b21854d2d14954b155f61182d288eefd4996 +size 4920734336 diff --git a/llama3-8b-cpt-sealionv2-base.Q4_K_S.gguf b/llama3-8b-cpt-sealionv2-base.Q4_K_S.gguf new file mode 100644 index 0000000..1e12299 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3740fcb2dfb073edd32f2e8f97163762e55c84e02e40c6c6049d2617544982 +size 4692669056 diff --git a/llama3-8b-cpt-sealionv2-base.Q5_K_M.gguf b/llama3-8b-cpt-sealionv2-base.Q5_K_M.gguf new file mode 100644 index 0000000..ca4c691 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb3e200d3e7cc29a150f8900185ffbe0538e1ac43fc00d711d771f10f45e2dc +size 5732987520 diff --git a/llama3-8b-cpt-sealionv2-base.Q5_K_S.gguf b/llama3-8b-cpt-sealionv2-base.Q5_K_S.gguf new file mode 100644 index 0000000..e04a16a --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80e2384fa83d357c067a0acead23a14233b0415b3e41c309c7f6d9c435449ee +size 5599294080 diff --git a/llama3-8b-cpt-sealionv2-base.Q6_K.gguf b/llama3-8b-cpt-sealionv2-base.Q6_K.gguf new file mode 100644 index 0000000..ac8c343 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0c714bdb57920bc1ec892d50939c61ce6326c30c0ce6917ee789df8b00eb213 +size 6596006528 diff --git a/llama3-8b-cpt-sealionv2-base.Q8_0.gguf b/llama3-8b-cpt-sealionv2-base.Q8_0.gguf new file mode 100644 index 0000000..2d0b521 --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773a194a306f6d0fe3c5b518e20977ffd1c126ebcc7d0b4a405f41677a4f75fb +size 8540770944 diff --git a/llama3-8b-cpt-sealionv2-base.f16.gguf b/llama3-8b-cpt-sealionv2-base.f16.gguf new file mode 100644 index 0000000..c96002e --- /dev/null +++ b/llama3-8b-cpt-sealionv2-base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a57a8d68ee46eb0404696eadbb01a386a62b0dcd2ebb217282ecdc639caa96 +size 16068891264