From 813f304817dcf0c0190a96b66c6415cf64f14499 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 4 Oct 2026 21:31:19 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/SmartAgent-Llama-3.1-8B-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++++ README.md | 64 +++++++++++++++++++++++++++++ SmartAgent-Llama-3.1-8B.IQ4_XS.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q2_K.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q3_K_L.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q3_K_M.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q3_K_S.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q4_K_M.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q4_K_S.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q5_K_M.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q5_K_S.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q6_K.gguf | 3 ++ SmartAgent-Llama-3.1-8B.Q8_0.gguf | 3 ++ SmartAgent-Llama-3.1-8B.f16.gguf | 3 ++ 14 files changed, 147 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 SmartAgent-Llama-3.1-8B.IQ4_XS.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q2_K.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q3_K_L.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q3_K_M.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q3_K_S.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q4_K_M.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q4_K_S.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q5_K_M.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q5_K_S.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q6_K.gguf create mode 100644 SmartAgent-Llama-3.1-8B.Q8_0.gguf create mode 100644 SmartAgent-Llama-3.1-8B.f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1b2aa66 --- /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 +SmartAgent-Llama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmartAgent-Llama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3a495da --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: emrecanacikgoz/SMARTAgent-Llama-3.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/emrecanacikgoz/SMARTAgent-Llama-3.1-8B + + +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/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmartAgent-Llama-3.1-8B-GGUF/resolve/main/SmartAgent-Llama-3.1-8B.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/SmartAgent-Llama-3.1-8B.IQ4_XS.gguf b/SmartAgent-Llama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..d53f969 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d3d95697e5b5815cfc18e50daab8bb4f630fc3636392330e5e30a59f2a2618 +size 4484367872 diff --git a/SmartAgent-Llama-3.1-8B.Q2_K.gguf b/SmartAgent-Llama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..d9ee3c4 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950163ee209dd69e2b4346b158db21709255d7dc8262b28e7e801b3d73faf200 +size 3179136512 diff --git a/SmartAgent-Llama-3.1-8B.Q3_K_L.gguf b/SmartAgent-Llama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..c4e3167 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f48fc135faf8f5c9e3bbfdbef6f44f0428b0c32cd5fb8d05d74f16dfe5042277 +size 4321961472 diff --git a/SmartAgent-Llama-3.1-8B.Q3_K_M.gguf b/SmartAgent-Llama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..f7b1bc6 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab0d0dd344aa49a11e576410f2e46988bdbb6271318929c169031469e5d9007 +size 4018923008 diff --git a/SmartAgent-Llama-3.1-8B.Q3_K_S.gguf b/SmartAgent-Llama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..25e8175 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5d93c61b7fea02c1733989b7129d2406763eb51569996c5bbe454b983278d79 +size 3664504320 diff --git a/SmartAgent-Llama-3.1-8B.Q4_K_M.gguf b/SmartAgent-Llama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..a671dec --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd60b960e53354af1137e1a615514ae055fa3f1c390b606936a784981be16ec8 +size 4920739328 diff --git a/SmartAgent-Llama-3.1-8B.Q4_K_S.gguf b/SmartAgent-Llama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..85a5162 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88864b989e9d83afdfd8d1c9d2d1d9c9217297ed45cb04eff3b30fd191d5f20a +size 4692674048 diff --git a/SmartAgent-Llama-3.1-8B.Q5_K_M.gguf b/SmartAgent-Llama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..3518b0f --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75361c62ed6f8420254bf7bfb4e567a278b5835554045833f85080960f872f80 +size 5732992512 diff --git a/SmartAgent-Llama-3.1-8B.Q5_K_S.gguf b/SmartAgent-Llama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..9800911 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c616da0b3363186efba3df5eb55ba20018656a545cf27f9846896e4bcc90ec5 +size 5599299072 diff --git a/SmartAgent-Llama-3.1-8B.Q6_K.gguf b/SmartAgent-Llama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..b5d9108 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76f5a1d8c3a4b798130fd2a05a54b7e5f5c1f355f1155526cc291a386980aaea +size 6596011520 diff --git a/SmartAgent-Llama-3.1-8B.Q8_0.gguf b/SmartAgent-Llama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..e835db5 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98c684df1463b5d5a06f87a7185383eabdc59888a0125e991a920e0b9833a4a7 +size 8540775936 diff --git a/SmartAgent-Llama-3.1-8B.f16.gguf b/SmartAgent-Llama-3.1-8B.f16.gguf new file mode 100644 index 0000000..adccb33 --- /dev/null +++ b/SmartAgent-Llama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee972b345ed709d6ba393c7cea7a820f7dc85f4c306e1189bccee42588e6a84c +size 16068896256