commit 0e9cd9b0100527758e91c72205161ff055cb80d4 Author: ModelHub XC Date: Wed Jul 8 16:33:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CataLlama-v0.2-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d33acd8 --- /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 +CataLlama-v0.2-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.2-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CataLlama-v0.2-Base.IQ3_M.gguf b/CataLlama-v0.2-Base.IQ3_M.gguf new file mode 100644 index 0000000..e38469a --- /dev/null +++ b/CataLlama-v0.2-Base.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3800fcb127bc3b4bb3bff5acdbb00a7669fec246a045dc6f82fa451fed51b8 +size 3784823520 diff --git a/CataLlama-v0.2-Base.IQ3_S.gguf b/CataLlama-v0.2-Base.IQ3_S.gguf new file mode 100644 index 0000000..a807a9b --- /dev/null +++ b/CataLlama-v0.2-Base.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386c33e5b035fef9065b7b0facb978760326e3e1951d2e3b4017b979584e790a +size 3682325216 diff --git a/CataLlama-v0.2-Base.IQ3_XS.gguf b/CataLlama-v0.2-Base.IQ3_XS.gguf new file mode 100644 index 0000000..12c3710 --- /dev/null +++ b/CataLlama-v0.2-Base.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e103328d657dc857f76625fcbbae0143a27906dddcb8bccff15ffad525662ac +size 3518747360 diff --git a/CataLlama-v0.2-Base.IQ4_XS.gguf b/CataLlama-v0.2-Base.IQ4_XS.gguf new file mode 100644 index 0000000..61b47f6 --- /dev/null +++ b/CataLlama-v0.2-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c00460043137ebe86c7e61c9381f713ee65be5be8c616b19b31d4e1e0ebe4b3 +size 4484362976 diff --git a/CataLlama-v0.2-Base.Q2_K.gguf b/CataLlama-v0.2-Base.Q2_K.gguf new file mode 100644 index 0000000..7bfc403 --- /dev/null +++ b/CataLlama-v0.2-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff6434021e278c277a995718990c509407357c1d85f4bb5c122fdc094ec4eaeb +size 3179131616 diff --git a/CataLlama-v0.2-Base.Q3_K_L.gguf b/CataLlama-v0.2-Base.Q3_K_L.gguf new file mode 100644 index 0000000..4648230 --- /dev/null +++ b/CataLlama-v0.2-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:575a177886db8d86434eea2dd4e8806cb74c14a5e77dd502bbe913695022d418 +size 4321956576 diff --git a/CataLlama-v0.2-Base.Q3_K_M.gguf b/CataLlama-v0.2-Base.Q3_K_M.gguf new file mode 100644 index 0000000..6fc3651 --- /dev/null +++ b/CataLlama-v0.2-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb05d99f96f312230f9f9bcad4b6a637b978f78ddf6b830262c1a9cc2972276 +size 4018918112 diff --git a/CataLlama-v0.2-Base.Q3_K_S.gguf b/CataLlama-v0.2-Base.Q3_K_S.gguf new file mode 100644 index 0000000..c3a93ad --- /dev/null +++ b/CataLlama-v0.2-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be7f00fad327803d93745b6f2c054080adb8c2eeb6ba1808dea1f5fd9d32882 +size 3664499424 diff --git a/CataLlama-v0.2-Base.Q4_K_M.gguf b/CataLlama-v0.2-Base.Q4_K_M.gguf new file mode 100644 index 0000000..ec00910 --- /dev/null +++ b/CataLlama-v0.2-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b13a53488dd0e76b81a8806e17cad5ba0f9caee38b902a51c287392ed0e06dca +size 4920734432 diff --git a/CataLlama-v0.2-Base.Q4_K_S.gguf b/CataLlama-v0.2-Base.Q4_K_S.gguf new file mode 100644 index 0000000..8d9b2e1 --- /dev/null +++ b/CataLlama-v0.2-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09cf154c1581a31e6fc613b5f8505ea1bfd839349053a210a3b9e823af9147f3 +size 4692669152 diff --git a/CataLlama-v0.2-Base.Q5_K_M.gguf b/CataLlama-v0.2-Base.Q5_K_M.gguf new file mode 100644 index 0000000..8260026 --- /dev/null +++ b/CataLlama-v0.2-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bcf1d32380d8c7d24734c0b39ee8bf947b213348a22d1b6dd6edd69c66f860b +size 5732987616 diff --git a/CataLlama-v0.2-Base.Q5_K_S.gguf b/CataLlama-v0.2-Base.Q5_K_S.gguf new file mode 100644 index 0000000..5518a15 --- /dev/null +++ b/CataLlama-v0.2-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5b0b7f8fd3a0c6b5c2f983ecf02fdec88c671ae2ac29a7f710af60073bd7190 +size 5599294176 diff --git a/CataLlama-v0.2-Base.Q6_K.gguf b/CataLlama-v0.2-Base.Q6_K.gguf new file mode 100644 index 0000000..48cdfc3 --- /dev/null +++ b/CataLlama-v0.2-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b917024153d3183898113a9fa58b4758f3043e065d70b08183c07f8fc0a6d6 +size 6596006624 diff --git a/CataLlama-v0.2-Base.Q8_0.gguf b/CataLlama-v0.2-Base.Q8_0.gguf new file mode 100644 index 0000000..684bebe --- /dev/null +++ b/CataLlama-v0.2-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1df571ad62b5e07df847750022b03af1dd0d202c40b18ed1072398b88c0175b +size 8540771040 diff --git a/CataLlama-v0.2-Base.f16.gguf b/CataLlama-v0.2-Base.f16.gguf new file mode 100644 index 0000000..a139e52 --- /dev/null +++ b/CataLlama-v0.2-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:471f8bce0b60327dc58700a3a9d8d0b8b3dc94cc5148d038b540a221063ae600 +size 16068891360 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cf0d134 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: catallama/CataLlama-v0.2-Base +language: +- ca +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- llama +- llama-3 +- Catalan +--- +## About + + + + + + +static quants of https://huggingface.co/catallama/CataLlama-v0.2-Base + + +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/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.2-Base-GGUF/resolve/main/CataLlama-v0.2-Base.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. + +