commit 77a33493e9c067dec4757e9eb2eb4ae6cf864e33 Author: ModelHub XC Date: Mon Jun 15 01:41:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9c16512 --- /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 +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..92c0ce8 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: MiraiShiftLab/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/MiraiShiftLab/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1-GGUF/resolve/main/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.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/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.IQ4_XS.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..f5bf173 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34195fac1ad88ee13c0289183e93fccd07a7c7f646591e7db12f59333777a2cd +size 4484364096 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q2_K.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q2_K.gguf new file mode 100644 index 0000000..306a91f --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458eb8fc51e1c6c75f08a9be288ded999cd2392e86b326b01a656c39c9d916d2 +size 3179132736 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_L.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..f766bbb --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a25c838dbe8ba0956ab8f616121a67bc222de50a0b8cc7002da12141586aac +size 4321957696 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_M.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..73a0da0 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f4fd7ebab9ce8a3e798d568f8b2e036544827c3f9c6403c3f0724a41cdb80b +size 4018919232 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_S.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..b94a475 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:875377cc6d849430779bb71d2c2fcd0dfe6fd2aba27937221462629ff91e7110 +size 3664500544 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_M.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..fc16a12 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24cba8bac4c11375975ac64946fee077dce353432a38071c00d780cb1e75dea8 +size 4920735552 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_S.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..a262d65 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d86c904ad63d1874ffe3ab5dbac3762142dfbdbb62cb68830f83daa1deb188 +size 4692670272 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_M.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..b8ba1b5 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d02d0ae94cb16837f8cdbd4cbc828bcc40822d0ce3595fda98f89cae4fc587ba +size 5732988736 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_S.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..76f25b6 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f133adf3df7b11f2b3021fc19e2744ec2b076b9de63e7ca8914453e47ddb770 +size 5599295296 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q6_K.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q6_K.gguf new file mode 100644 index 0000000..136aab5 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4447e2f4e06a6f85fdcf2d59545cdea5c35ab827231fc5a6e624b2f8bb022faa +size 6596007744 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q8_0.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q8_0.gguf new file mode 100644 index 0000000..e433532 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edffe24feba1f501952f9adf02553483b62a75b4f4bd0098c29a0d533e84a47f +size 8540772160 diff --git a/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.f16.gguf b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.f16.gguf new file mode 100644 index 0000000..27e9681 --- /dev/null +++ b/llama-3.1-Swallow-Amateras-8b-Instruct-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ab0fb268491a28f9f7c6e6893879b9d5687dc919482d803af8b94985f895faa +size 16068892480