commit 62b57e8c00066a4d3dd8341e13d96efe7bb062c6 Author: ModelHub XC Date: Tue Jun 23 23:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d270a40 --- /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 +S1-Llama-3.2-3Bx4-MoE.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.f16.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +S1-Llama-3.2-3Bx4-MoE.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4402c0b --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: cloudyu/S1-Llama-3.2-3Bx4-MoE +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/cloudyu/S1-Llama-3.2-3Bx4-MoE + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-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/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q2_K.gguf) | Q2_K | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q3_K_M.gguf) | Q3_K_M | 4.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q4_K_M.gguf) | Q4_K_M | 6.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q5_K_S.gguf) | Q5_K_S | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q5_K_M.gguf) | Q5_K_M | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q6_K.gguf) | Q6_K | 7.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.Q8_0.gguf) | Q8_0 | 10.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/S1-Llama-3.2-3Bx4-MoE-GGUF/resolve/main/S1-Llama-3.2-3Bx4-MoE.f16.gguf) | f16 | 19.2 | 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/S1-Llama-3.2-3Bx4-MoE.IQ4_XS.gguf b/S1-Llama-3.2-3Bx4-MoE.IQ4_XS.gguf new file mode 100644 index 0000000..d8ab175 --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ed6f8b985a11219bfef241293e3a888193bd422dcf7279e7c9efeeb1e47c822 +size 5246746720 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q2_K.gguf b/S1-Llama-3.2-3Bx4-MoE.Q2_K.gguf new file mode 100644 index 0000000..367e1ed --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa48733a33d75870beff74490aea9516f6f0c2531f6b6bbfca15948d4a27fbf +size 3660906592 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q3_K_L.gguf b/S1-Llama-3.2-3Bx4-MoE.Q3_K_L.gguf new file mode 100644 index 0000000..b2dec4a --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32fcf78c8f074efbbfc1cb1a820801dd531e22fafa1667a135adc41ace4d6be8 +size 5086707808 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q3_K_M.gguf b/S1-Llama-3.2-3Bx4-MoE.Q3_K_M.gguf new file mode 100644 index 0000000..1d6e95a --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5e65a457aea0b5980c3f83aa82ef4b821df264505db3757b6dfb9f47bebf1a3 +size 4703715424 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q3_K_S.gguf b/S1-Llama-3.2-3Bx4-MoE.Q3_K_S.gguf new file mode 100644 index 0000000..cc9cd42 --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6de4122fd6ab7cf06d98289f525de1413353bb01bb9d80e4ea4503d16b5e329 +size 4269211744 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q4_K_M.gguf b/S1-Llama-3.2-3Bx4-MoE.Q4_K_M.gguf new file mode 100644 index 0000000..8417498 --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23b38cb7a5cfad7a6bcc025482871250c16179b8e14668d2bcd99ca477014ca3 +size 5860507744 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q4_K_S.gguf b/S1-Llama-3.2-3Bx4-MoE.Q4_K_S.gguf new file mode 100644 index 0000000..6a2ed31 --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa1b58b63df771d0697d39b75eb2e439e1ba619efa3ddb37a7538f085babea8e +size 5525143648 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q5_K_M.gguf b/S1-Llama-3.2-3Bx4-MoE.Q5_K_M.gguf new file mode 100644 index 0000000..0f71ebd --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b759d208129cbad7032e0c7bcae2a47f243dd7c55d6a6332e12805e44f251b2a +size 6823886944 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q5_K_S.gguf b/S1-Llama-3.2-3Bx4-MoE.Q5_K_S.gguf new file mode 100644 index 0000000..941623d --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:509687409cf33dd914401d26254b0d6858434adab703992d617fdaf16df4485b +size 6630867040 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q6_K.gguf b/S1-Llama-3.2-3Bx4-MoE.Q6_K.gguf new file mode 100644 index 0000000..625a831 --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32e50ca1da2b31833bf99918f50377fa06cf48e267179ac883cdb1fb1bf56541 +size 7847477344 diff --git a/S1-Llama-3.2-3Bx4-MoE.Q8_0.gguf b/S1-Llama-3.2-3Bx4-MoE.Q8_0.gguf new file mode 100644 index 0000000..ba873f5 --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250709cc58521a686a2185b7ab5203beff6bf2e0687a30f30c54e4e5659eef74 +size 10161424480 diff --git a/S1-Llama-3.2-3Bx4-MoE.f16.gguf b/S1-Llama-3.2-3Bx4-MoE.f16.gguf new file mode 100644 index 0000000..a59e3fb --- /dev/null +++ b/S1-Llama-3.2-3Bx4-MoE.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b06d621b32eea4432ebe9aa97a94e3006f0a68fb41a3ed06c0575752de0010a +size 19118639200