commit e4f5daae379c23ce9dae0b00645b9484293df8ad Author: ModelHub XC Date: Thu Jul 30 23:43:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..37a53eb --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-3.1-Swallow-8B-v0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-v0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Swallow-8B-v0.2.IQ4_XS.gguf b/Llama-3.1-Swallow-8B-v0.2.IQ4_XS.gguf new file mode 100644 index 0000000..c4b7f6b --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf6749de38c1c392ad5d733e04b12f83c24e015ee5cc9fd33633bc3dfea80302 +size 4484363296 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q2_K.gguf b/Llama-3.1-Swallow-8B-v0.2.Q2_K.gguf new file mode 100644 index 0000000..6fba3d7 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de8eb6f1c7e01667716117441399a98ca9892b15a6993adebf691ac17e3e4405 +size 3179131936 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q3_K_L.gguf b/Llama-3.1-Swallow-8B-v0.2.Q3_K_L.gguf new file mode 100644 index 0000000..8861a0f --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89879e059344555b4aa6fd11c8732852f6e5fecc99af0894c593862f30852770 +size 4321956896 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q3_K_M.gguf b/Llama-3.1-Swallow-8B-v0.2.Q3_K_M.gguf new file mode 100644 index 0000000..5879ca5 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada2bb9ce780e90b8df8bc2b78f06a3a6515de5364d2cedc9c05c1331d47761d +size 4018918432 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q3_K_S.gguf b/Llama-3.1-Swallow-8B-v0.2.Q3_K_S.gguf new file mode 100644 index 0000000..8054f64 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e4ae895e82a440598754bd24e5b2223d54255cb88ca4866914dba4d747ab51 +size 3664499744 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q4_0_4_4.gguf b/Llama-3.1-Swallow-8B-v0.2.Q4_0_4_4.gguf new file mode 100644 index 0000000..d755d2a --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c749a395666b134fdf459c91e1eeccfb8c84cf541eaf137df1939fe022723c6 +size 4661212192 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q4_K_M.gguf b/Llama-3.1-Swallow-8B-v0.2.Q4_K_M.gguf new file mode 100644 index 0000000..133c12e --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e7702d0b8bd0b8ed645d58b801a4f05ed9a9474ff763a2ad2e6791171f01011 +size 4920734752 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q4_K_S.gguf b/Llama-3.1-Swallow-8B-v0.2.Q4_K_S.gguf new file mode 100644 index 0000000..4eb905f --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c4d0c2a36e7dea66f6836f225a9a04e45e249bb6ec241c8d1fdb67cf88689d +size 4692669472 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q5_K_M.gguf b/Llama-3.1-Swallow-8B-v0.2.Q5_K_M.gguf new file mode 100644 index 0000000..ef8cfd0 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f486e89ea72b75b3b89aa84bb714e7a7d6af3b0531e06a629748a70d7bb89d06 +size 5732987936 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q5_K_S.gguf b/Llama-3.1-Swallow-8B-v0.2.Q5_K_S.gguf new file mode 100644 index 0000000..8941eea --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20eddfd36f15767a8c7b2958f945bef71069c4e3ad1a32ed824c15be4e59a8db +size 5599294496 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q6_K.gguf b/Llama-3.1-Swallow-8B-v0.2.Q6_K.gguf new file mode 100644 index 0000000..d75de2a --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e5eeb544a721354af3fd3d139a08316091e45946b2b0646160bdde780867ad +size 6596006944 diff --git a/Llama-3.1-Swallow-8B-v0.2.Q8_0.gguf b/Llama-3.1-Swallow-8B-v0.2.Q8_0.gguf new file mode 100644 index 0000000..3308035 --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2330134639d1758b2ded3a86bc5311a7ac0f979dd485621ec59a6a80239ae54a +size 8540771360 diff --git a/Llama-3.1-Swallow-8B-v0.2.f16.gguf b/Llama-3.1-Swallow-8B-v0.2.f16.gguf new file mode 100644 index 0000000..fda6a5a --- /dev/null +++ b/Llama-3.1-Swallow-8B-v0.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec3b6fa9c6e2487f274feafd52a80936f6dce2f75384b2a702230d49e7d6ff6 +size 16068891680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e9d0ead --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: tokyotech-llm/Llama-3.1-Swallow-8B-v0.2 +language: +- en +- ja +library_name: transformers +license: llama3.1 +model_type: llama +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-v0.2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-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-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-v0.2.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. + +