commit 1c7ef30f4b2cdab473c7828a4f01e6783dd5b387 Author: ModelHub XC Date: Tue Jun 16 18:03:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c506b66 --- /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-Instruct-v0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.IQ4_XS.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.IQ4_XS.gguf new file mode 100644 index 0000000..e5e077a --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:198c55930836180be4715a73157fe143a9ab25b10514e2613e22d704879b7469 +size 4484363968 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q2_K.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q2_K.gguf new file mode 100644 index 0000000..1d22b69 --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8205ebd892b9dec55db8210d958f37553b58ee8a585d4075f1776ca2717a79f +size 3179132608 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_L.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_L.gguf new file mode 100644 index 0000000..567f636 --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c62755258fba0c28f4c15026cdd67d8ced8fd3d2b72d079ebe116e85901940b +size 4321957568 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_M.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_M.gguf new file mode 100644 index 0000000..50f062d --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce5bbbf297029e44e1413bf68011beeb5a6f1c5a77815571d55f22a1d399bc16 +size 4018919104 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_S.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_S.gguf new file mode 100644 index 0000000..8d3f56a --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d629c263ed88db35e4e90242989409a261040681681872e5acf312db1fb63ed8 +size 3664500416 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_0_4_4.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_0_4_4.gguf new file mode 100644 index 0000000..7a324af --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:858c5b2a598faead77c89410adba1abe85bf64ac7217e7ac66027a087ce2d034 +size 4661212864 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_K_M.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_K_M.gguf new file mode 100644 index 0000000..976296a --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee9bd478a43d21c31d233e1cd0ab0373d6dd5f697c0c90c143bc4757a9ed7cf +size 4920735424 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_K_S.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_K_S.gguf new file mode 100644 index 0000000..9cccddd --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e94d50b7cd6bd666046e90ae804abcf3f55d4015b7254f80f873aed8a406cd +size 4692670144 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_M.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_M.gguf new file mode 100644 index 0000000..eef5d27 --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bef9217bc36b406306f38a0d0626db4fc86a4566e12239393de39de033cbac62 +size 5732988608 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_S.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_S.gguf new file mode 100644 index 0000000..8ecade5 --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aaa87f51a48849a3516b682c1f799765a733db2fe9f50c32d08809bd1a2b5bd +size 5599295168 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q6_K.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q6_K.gguf new file mode 100644 index 0000000..d5b311d --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf987973137f15828ba6d31863dfbd084286e24dfd7899c8ac6a4257e0ce880 +size 6596007616 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.Q8_0.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q8_0.gguf new file mode 100644 index 0000000..b790247 --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f09ba2b047f534c37b287ab3d42909134e551403341c90c50351ff732854c6 +size 8540772032 diff --git a/Llama-3.1-Swallow-8B-Instruct-v0.2.f16.gguf b/Llama-3.1-Swallow-8B-Instruct-v0.2.f16.gguf new file mode 100644 index 0000000..2ae9413 --- /dev/null +++ b/Llama-3.1-Swallow-8B-Instruct-v0.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f33690ee0f55d7dc74be4aa5c8bbf72a56269209263935de8e65bea77b86c9a +size 16068892352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b416589 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2 +datasets: +- lmsys/lmsys-chat-1m +- tokyotech-llm/lmsys-chat-1m-synth +- argilla/magpie-ultra-v0.1 +- tokyotech-llm/swallow-magpie-ultra-v0.1 +- tokyotech-llm/swallow-gemma-magpie-v0.1 +language: +- en +- ja +library_name: transformers +license: +- llama3.1 +- gemma +model_type: llama +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-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-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-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-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-v0.2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Swallow-8B-Instruct-v0.2-GGUF/resolve/main/Llama-3.1-Swallow-8B-Instruct-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. + +