commit 5a8fcc6109723c1c91f8676db2bb063d8c010176 Author: ModelHub XC Date: Thu Sep 24 09:13:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..47623be --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +SmartLlama-3-8B-MS-v0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.f16.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +SmartLlama-3-8B-MS-v0.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..37938bc --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Kukedlc/SmartLlama-3-8B-MS-v0.2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +--- +## About + + + + + +static quants of https://huggingface.co/Kukedlc/SmartLlama-3-8B-MS-v0.2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-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/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-v0.2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SmartLlama-3-8B-MS-v0.2-GGUF/resolve/main/SmartLlama-3-8B-MS-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. + + diff --git a/SmartLlama-3-8B-MS-v0.2.IQ3_M.gguf b/SmartLlama-3-8B-MS-v0.2.IQ3_M.gguf new file mode 100644 index 0000000..73b82fe --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18856e9f95d86d94ec82e61a78159b46bb10ed5f031f223b823e7d01a1405856 +size 3785336128 diff --git a/SmartLlama-3-8B-MS-v0.2.IQ3_S.gguf b/SmartLlama-3-8B-MS-v0.2.IQ3_S.gguf new file mode 100644 index 0000000..cf11834 --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4fcf06bb032e4531f643a5bba49f2af908114505e8e5e2418f6a95b54e9e272 +size 3682837824 diff --git a/SmartLlama-3-8B-MS-v0.2.IQ3_XS.gguf b/SmartLlama-3-8B-MS-v0.2.IQ3_XS.gguf new file mode 100644 index 0000000..3bd3ce7 --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9f1e08267025befe47da9c9a56182e0d1dbb6232873ed37c9a6ec424cba65d +size 3519259968 diff --git a/SmartLlama-3-8B-MS-v0.2.IQ4_XS.gguf b/SmartLlama-3-8B-MS-v0.2.IQ4_XS.gguf new file mode 100644 index 0000000..49e4219 --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85fdf6aa7be5314bca98ae8d00751c5d08e410625eab4217d48bfb62d27b2138 +size 4484875584 diff --git a/SmartLlama-3-8B-MS-v0.2.Q2_K.gguf b/SmartLlama-3-8B-MS-v0.2.Q2_K.gguf new file mode 100644 index 0000000..7e6d281 --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f497aa75fe1d836156c78d1674f47679bafb1aadca8224e3a9a598c0f1612759 +size 3179644224 diff --git a/SmartLlama-3-8B-MS-v0.2.Q3_K_L.gguf b/SmartLlama-3-8B-MS-v0.2.Q3_K_L.gguf new file mode 100644 index 0000000..7a194fd --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac241a54bc02309904a7f52391136c76e2827e0b1f778882bb15d272b7e0db8a +size 4322469184 diff --git a/SmartLlama-3-8B-MS-v0.2.Q3_K_M.gguf b/SmartLlama-3-8B-MS-v0.2.Q3_K_M.gguf new file mode 100644 index 0000000..74c5d91 --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee227c408347718fb7ad1220a388859c09e76d4f0e88dc4a53e24ae0e3cc864 +size 4019430720 diff --git a/SmartLlama-3-8B-MS-v0.2.Q3_K_S.gguf b/SmartLlama-3-8B-MS-v0.2.Q3_K_S.gguf new file mode 100644 index 0000000..a5edb14 --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eee01d7e764b7a28071e0111a1d1c7e778814bb79b91d3311c4259a49dea6ff +size 3665012032 diff --git a/SmartLlama-3-8B-MS-v0.2.Q4_K_M.gguf b/SmartLlama-3-8B-MS-v0.2.Q4_K_M.gguf new file mode 100644 index 0000000..3120c8f --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafb792862de3ae7db7268d8ebb11fa8a4869cf6a57cc4ee50760776e28ba730 +size 4921247040 diff --git a/SmartLlama-3-8B-MS-v0.2.Q4_K_S.gguf b/SmartLlama-3-8B-MS-v0.2.Q4_K_S.gguf new file mode 100644 index 0000000..3870bdd --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5021a84454d2013714a2f9c73342d9f1ef0a528b96b1b6531184bbcd404aac91 +size 4693181760 diff --git a/SmartLlama-3-8B-MS-v0.2.Q5_K_M.gguf b/SmartLlama-3-8B-MS-v0.2.Q5_K_M.gguf new file mode 100644 index 0000000..90e583b --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3909054b4753485987f3b0be5685b26fce6d2519b33476e911995a3450554b5e +size 5733500224 diff --git a/SmartLlama-3-8B-MS-v0.2.Q5_K_S.gguf b/SmartLlama-3-8B-MS-v0.2.Q5_K_S.gguf new file mode 100644 index 0000000..6d72e74 --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b2081341421ca57e7f59549b2bc55b9073f5b4f6a9eb5319f98d20ceb8ff89 +size 5599806784 diff --git a/SmartLlama-3-8B-MS-v0.2.Q6_K.gguf b/SmartLlama-3-8B-MS-v0.2.Q6_K.gguf new file mode 100644 index 0000000..5f15c79 --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a73919650b13494fae0863ddef40dd6645499a616d112490c2277721adcdbb +size 6596519232 diff --git a/SmartLlama-3-8B-MS-v0.2.Q8_0.gguf b/SmartLlama-3-8B-MS-v0.2.Q8_0.gguf new file mode 100644 index 0000000..75f501f --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a114545aa36a4a52c8640c8c8bd5228103fc62496236272c3ec97dbb0eef195f +size 8541283648 diff --git a/SmartLlama-3-8B-MS-v0.2.f16.gguf b/SmartLlama-3-8B-MS-v0.2.f16.gguf new file mode 100644 index 0000000..6f2908c --- /dev/null +++ b/SmartLlama-3-8B-MS-v0.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:770685dcd09c609de5b3a736915a8be8389dbdddc7e609ac1c708015e356c4d5 +size 16069403968