commit c111eda00a3cbff79d44650978bc896bafab1daa Author: ModelHub XC Date: Sat Jun 27 03:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Clara-v2-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b9adb5a --- /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 +Clara-v2-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Clara-v2-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Clara-v2-8B.IQ4_XS.gguf b/Clara-v2-8B.IQ4_XS.gguf new file mode 100644 index 0000000..9fbf1f8 --- /dev/null +++ b/Clara-v2-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fc2656ab3ea9bb635047cfac733e6d369d48640b1eecec87b858e252b07bcd6 +size 4861239616 diff --git a/Clara-v2-8B.Q2_K.gguf b/Clara-v2-8B.Q2_K.gguf new file mode 100644 index 0000000..59f9abe --- /dev/null +++ b/Clara-v2-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:789d550d63eada07910b76e975b5f2c98ecd2e348b1c2c33ae879f39f134a044 +size 3412304192 diff --git a/Clara-v2-8B.Q3_K_L.gguf b/Clara-v2-8B.Q3_K_L.gguf new file mode 100644 index 0000000..e268b32 --- /dev/null +++ b/Clara-v2-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed0cfb95b1643f6109c504e5a4a35baf15765977a4a21dbd6ba657d7ddc82e8 +size 4699889984 diff --git a/Clara-v2-8B.Q3_K_M.gguf b/Clara-v2-8B.Q3_K_M.gguf new file mode 100644 index 0000000..59239c3 --- /dev/null +++ b/Clara-v2-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b916d94df97a51b0ae6549c22909ae2d1f688b7bbeb30e6324fa18745291288 +size 4347044160 diff --git a/Clara-v2-8B.Q3_K_S.gguf b/Clara-v2-8B.Q3_K_S.gguf new file mode 100644 index 0000000..046ad98 --- /dev/null +++ b/Clara-v2-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb019d926c28b0a1246c4b987124377896f7d71242508b7b9cadb49d3f79b81f +size 3942949184 diff --git a/Clara-v2-8B.Q4_K_M.gguf b/Clara-v2-8B.Q4_K_M.gguf new file mode 100644 index 0000000..fb67399 --- /dev/null +++ b/Clara-v2-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa6759346a96bb799e450638ca153856a5ef94f3e68a177cb7d78859bcd7eb6e +size 5347909952 diff --git a/Clara-v2-8B.Q4_K_S.gguf b/Clara-v2-8B.Q4_K_S.gguf new file mode 100644 index 0000000..c2d4f63 --- /dev/null +++ b/Clara-v2-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155ac1bf1e7aea55fee3e39b5b4bf014fe45103b12abc56840c530dc399bf418 +size 5090812224 diff --git a/Clara-v2-8B.Q5_K_M.gguf b/Clara-v2-8B.Q5_K_M.gguf new file mode 100644 index 0000000..ba3981f --- /dev/null +++ b/Clara-v2-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a7053261a3a23910e1cc921160efcf7bfba2b4b013a07a09e151acf1cf2c1b0 +size 6253879616 diff --git a/Clara-v2-8B.Q5_K_S.gguf b/Clara-v2-8B.Q5_K_S.gguf new file mode 100644 index 0000000..5036785 --- /dev/null +++ b/Clara-v2-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:512e4f9501758c77ded4b0008b6e1e10c9ad7e22fdc1b48abda67e62f5738d55 +size 6103474496 diff --git a/Clara-v2-8B.Q6_K.gguf b/Clara-v2-8B.Q6_K.gguf new file mode 100644 index 0000000..5387826 --- /dev/null +++ b/Clara-v2-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016f1da39269b78b4c3756ec5bda8620bcbb8dd8cf0048908e7bf85af52fd8ab +size 7216472384 diff --git a/Clara-v2-8B.Q8_0.gguf b/Clara-v2-8B.Q8_0.gguf new file mode 100644 index 0000000..d1abcf2 --- /dev/null +++ b/Clara-v2-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b730a870af30500b51b12b77424901748d1ac4068e4c68df24a3f5c1df1697c5 +size 9345605952 diff --git a/Clara-v2-8B.f16.gguf b/Clara-v2-8B.f16.gguf new file mode 100644 index 0000000..ef1c341 --- /dev/null +++ b/Clara-v2-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceba4df8a84611406c39bb161f82c1db5fde80ef3065e17b8064c9195a101e6a +size 17587413312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..40a22c3 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: ayan4m1/Clara-v2-8B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ayan4m1/Clara-v2-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Clara-v2-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Clara-v2-8B-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/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q2_K.gguf) | Q2_K | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q3_K_M.gguf) | Q3_K_M | 4.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.IQ4_XS.gguf) | IQ4_XS | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q4_K_S.gguf) | Q4_K_S | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q5_K_S.gguf) | Q5_K_S | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q5_K_M.gguf) | Q5_K_M | 6.4 | | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q6_K.gguf) | Q6_K | 7.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.Q8_0.gguf) | Q8_0 | 9.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Clara-v2-8B-GGUF/resolve/main/Clara-v2-8B.f16.gguf) | f16 | 17.7 | 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. + +