commit 73c11f85d284c2cadd7cc927523ff23e3ee32897 Author: ModelHub XC Date: Tue Jul 21 12:09:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/cocoruta-8b-llama3.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cb1bd8c --- /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 +cocoruta-8b-llama3.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cocoruta-8b-llama3.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..136aa43 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: felipeoes/cocoruta-8b-llama3.1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/felipeoes/cocoruta-8b-llama3.1 + + +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/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/cocoruta-8b-llama3.1-GGUF/resolve/main/cocoruta-8b-llama3.1.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/cocoruta-8b-llama3.1.IQ4_XS.gguf b/cocoruta-8b-llama3.1.IQ4_XS.gguf new file mode 100644 index 0000000..dbd2e4b --- /dev/null +++ b/cocoruta-8b-llama3.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fbff4f1b00a9cafa13e6151a6065c832a769f4692a94315589cd5369dc705ae +size 4484363648 diff --git a/cocoruta-8b-llama3.1.Q2_K.gguf b/cocoruta-8b-llama3.1.Q2_K.gguf new file mode 100644 index 0000000..e73f15c --- /dev/null +++ b/cocoruta-8b-llama3.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47b8b8d52370b22ecfd553b24c5f00c8acf2cc313e976397ba4c7cd4996709a8 +size 3179132288 diff --git a/cocoruta-8b-llama3.1.Q3_K_L.gguf b/cocoruta-8b-llama3.1.Q3_K_L.gguf new file mode 100644 index 0000000..e714f77 --- /dev/null +++ b/cocoruta-8b-llama3.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d86176aeb407974b7bf9327af5d359f9ddae48e3cc432597d4b3cce969f5d2ca +size 4321957248 diff --git a/cocoruta-8b-llama3.1.Q3_K_M.gguf b/cocoruta-8b-llama3.1.Q3_K_M.gguf new file mode 100644 index 0000000..264c7c8 --- /dev/null +++ b/cocoruta-8b-llama3.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:245b04258f6579758df697a0be2a5fcb252100f9be9a2a16db88980d7e7df2de +size 4018918784 diff --git a/cocoruta-8b-llama3.1.Q3_K_S.gguf b/cocoruta-8b-llama3.1.Q3_K_S.gguf new file mode 100644 index 0000000..03203f8 --- /dev/null +++ b/cocoruta-8b-llama3.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:223aecf3ce343e2faefdec4be9fd903f67c869c7f159ac77cea487148c91749d +size 3664500096 diff --git a/cocoruta-8b-llama3.1.Q4_K_M.gguf b/cocoruta-8b-llama3.1.Q4_K_M.gguf new file mode 100644 index 0000000..daac83b --- /dev/null +++ b/cocoruta-8b-llama3.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e964d96f205615864818fcfffcc8bcbe4f303adbcec5b4e9345b2d2693dedd3d +size 4920735104 diff --git a/cocoruta-8b-llama3.1.Q4_K_S.gguf b/cocoruta-8b-llama3.1.Q4_K_S.gguf new file mode 100644 index 0000000..2d29a3c --- /dev/null +++ b/cocoruta-8b-llama3.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f154b60ba1cf4a27f4d4bbc28f27d44b26d63085c566bb49097e3d57c9a3ea +size 4692669824 diff --git a/cocoruta-8b-llama3.1.Q5_K_M.gguf b/cocoruta-8b-llama3.1.Q5_K_M.gguf new file mode 100644 index 0000000..f4bfb61 --- /dev/null +++ b/cocoruta-8b-llama3.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a00590a515c5d1cb60fbc5dd4dd56107e58b5313afb97369d7d84643a8ace937 +size 5732988288 diff --git a/cocoruta-8b-llama3.1.Q5_K_S.gguf b/cocoruta-8b-llama3.1.Q5_K_S.gguf new file mode 100644 index 0000000..9abbb2a --- /dev/null +++ b/cocoruta-8b-llama3.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ef36f5c80c24f26312f169407e1ffd15af9e0e2a01479e455b2d130f25dd6d +size 5599294848 diff --git a/cocoruta-8b-llama3.1.Q6_K.gguf b/cocoruta-8b-llama3.1.Q6_K.gguf new file mode 100644 index 0000000..162e666 --- /dev/null +++ b/cocoruta-8b-llama3.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32276379b786fc135c562421e447b647a9da631647fde11dd7d38f3e9eb78251 +size 6596007296 diff --git a/cocoruta-8b-llama3.1.Q8_0.gguf b/cocoruta-8b-llama3.1.Q8_0.gguf new file mode 100644 index 0000000..0a691b5 --- /dev/null +++ b/cocoruta-8b-llama3.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6991398b34e602238660b0e6b80d26078503ec8ec3ae28a77151d1197c6801e3 +size 8540771712 diff --git a/cocoruta-8b-llama3.1.f16.gguf b/cocoruta-8b-llama3.1.f16.gguf new file mode 100644 index 0000000..bfbb63f --- /dev/null +++ b/cocoruta-8b-llama3.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7c2e97196b9c670cf00cdabf0dc3483eb09c5c142ee145c861b8466e6f9ee69 +size 16068892032