commit b711b979444161ca9af754f8062cae077dee6cff Author: ModelHub XC Date: Wed Jul 8 12:09:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CabraLlama3-8b-32k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..899a24a --- /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 +CabraLlama3-8b-32k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.f16.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +CabraLlama3-8b-32k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CabraLlama3-8b-32k.IQ3_M.gguf b/CabraLlama3-8b-32k.IQ3_M.gguf new file mode 100644 index 0000000..06e5e94 --- /dev/null +++ b/CabraLlama3-8b-32k.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9916f4ee143230a23692be3029dfaefcdc4105514bea32836ce6a595e49271 +size 3784823552 diff --git a/CabraLlama3-8b-32k.IQ3_S.gguf b/CabraLlama3-8b-32k.IQ3_S.gguf new file mode 100644 index 0000000..0bd0278 --- /dev/null +++ b/CabraLlama3-8b-32k.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419fb84f9ed1ec46411a2ff9b656122caba0dc1c13b5646b25e15c09464226d2 +size 3682325248 diff --git a/CabraLlama3-8b-32k.IQ3_XS.gguf b/CabraLlama3-8b-32k.IQ3_XS.gguf new file mode 100644 index 0000000..83679bc --- /dev/null +++ b/CabraLlama3-8b-32k.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7fca7186f744b82b09b0bb9fca8c19241f512b037c61af0b4b98b92e2035b79 +size 3518747392 diff --git a/CabraLlama3-8b-32k.IQ4_XS.gguf b/CabraLlama3-8b-32k.IQ4_XS.gguf new file mode 100644 index 0000000..f52a9d2 --- /dev/null +++ b/CabraLlama3-8b-32k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8a43b284663045d88efb6041c8ef296c0fe8d5192ea24da1f5a2645a143196 +size 4484363008 diff --git a/CabraLlama3-8b-32k.Q2_K.gguf b/CabraLlama3-8b-32k.Q2_K.gguf new file mode 100644 index 0000000..4e979cf --- /dev/null +++ b/CabraLlama3-8b-32k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5584a5304423be86f73cd58078ff636a1fcb1a71735715e000e4bfb947ad59c6 +size 3179131648 diff --git a/CabraLlama3-8b-32k.Q3_K_L.gguf b/CabraLlama3-8b-32k.Q3_K_L.gguf new file mode 100644 index 0000000..62eb77b --- /dev/null +++ b/CabraLlama3-8b-32k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935498c1cdee287eb6c1a4cb7938042333428bdbcf9392a8461137f08774b87e +size 4321956608 diff --git a/CabraLlama3-8b-32k.Q3_K_M.gguf b/CabraLlama3-8b-32k.Q3_K_M.gguf new file mode 100644 index 0000000..d7fa605 --- /dev/null +++ b/CabraLlama3-8b-32k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3344f8196e390ec4eb34d8ef3e765a5897e0986dec7ddb36ebfc4d117ab36548 +size 4018918144 diff --git a/CabraLlama3-8b-32k.Q3_K_S.gguf b/CabraLlama3-8b-32k.Q3_K_S.gguf new file mode 100644 index 0000000..1ad9b41 --- /dev/null +++ b/CabraLlama3-8b-32k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13c2bc2ddf77a2bb663f2fd5521def9f024759885a2f2d3e6bf821864a57ec9 +size 3664499456 diff --git a/CabraLlama3-8b-32k.Q4_K_M.gguf b/CabraLlama3-8b-32k.Q4_K_M.gguf new file mode 100644 index 0000000..e39d481 --- /dev/null +++ b/CabraLlama3-8b-32k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:670b28ea792ef16490d64cca49bd4d3fff2d1b5f0a66c84e0c18b15acf9caeb2 +size 4920734464 diff --git a/CabraLlama3-8b-32k.Q4_K_S.gguf b/CabraLlama3-8b-32k.Q4_K_S.gguf new file mode 100644 index 0000000..c8cf96e --- /dev/null +++ b/CabraLlama3-8b-32k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:986132247309c2e67b46373b30ef695da9689721fa7267eaf90d1da85e3dea98 +size 4692669184 diff --git a/CabraLlama3-8b-32k.Q5_K_M.gguf b/CabraLlama3-8b-32k.Q5_K_M.gguf new file mode 100644 index 0000000..f8ed6aa --- /dev/null +++ b/CabraLlama3-8b-32k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1726a014b74de058a559f65557575b6b4589b742d8a2256e4da0aa2ae1c8279 +size 5732987648 diff --git a/CabraLlama3-8b-32k.Q5_K_S.gguf b/CabraLlama3-8b-32k.Q5_K_S.gguf new file mode 100644 index 0000000..a0712c2 --- /dev/null +++ b/CabraLlama3-8b-32k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f1397fb72bfdbc73aa008501882581d6e9ac63469af0aad5a4e8ece59a64854 +size 5599294208 diff --git a/CabraLlama3-8b-32k.Q6_K.gguf b/CabraLlama3-8b-32k.Q6_K.gguf new file mode 100644 index 0000000..1a22120 --- /dev/null +++ b/CabraLlama3-8b-32k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114d1d4e7c939e09a3f2ddd523cd651f11c39b837f7741a2f0d8695e2a6972ff +size 6596006656 diff --git a/CabraLlama3-8b-32k.Q8_0.gguf b/CabraLlama3-8b-32k.Q8_0.gguf new file mode 100644 index 0000000..b26c431 --- /dev/null +++ b/CabraLlama3-8b-32k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc1bd4446bd039720a2457349e32f03486e01c195dc15262a425e52fb69625b1 +size 8540771072 diff --git a/CabraLlama3-8b-32k.f16.gguf b/CabraLlama3-8b-32k.f16.gguf new file mode 100644 index 0000000..8eff7e3 --- /dev/null +++ b/CabraLlama3-8b-32k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d65e7cc758107e5485f5a16c177cb8ca4f3ff1cba35dd11503f7fa2794d751 +size 16068891392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cbc9d9d --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: nicolasdec/CabraLlama3-8b-32k +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/nicolasdec/CabraLlama3-8b-32k + + +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/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CabraLlama3-8b-32k-GGUF/resolve/main/CabraLlama3-8b-32k.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. + +