commit 4caf31f97c3e2e3f9d0b7de80b0e2a6603b04444 Author: ModelHub XC Date: Wed Sep 9 13:22:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CataLlama-v0.1-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b0d1860 --- /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 +CataLlama-v0.1-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CataLlama-v0.1-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CataLlama-v0.1-Base.IQ4_XS.gguf b/CataLlama-v0.1-Base.IQ4_XS.gguf new file mode 100644 index 0000000..54bbb6b --- /dev/null +++ b/CataLlama-v0.1-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e19359f7c612ab48fcbd5d6dae0d71484517a279f40593711b60a1d1df4b1fb +size 4484369504 diff --git a/CataLlama-v0.1-Base.Q2_K.gguf b/CataLlama-v0.1-Base.Q2_K.gguf new file mode 100644 index 0000000..31fb1e0 --- /dev/null +++ b/CataLlama-v0.1-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a7a3037ca5203fd8586c0b163b4193b325b6f4318de4647ce35043a9a15058 +size 3179137312 diff --git a/CataLlama-v0.1-Base.Q3_K_L.gguf b/CataLlama-v0.1-Base.Q3_K_L.gguf new file mode 100644 index 0000000..2f43d04 --- /dev/null +++ b/CataLlama-v0.1-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4fbe6edef29dfef0dae27b978e1109cef417586e7b701869bd962a605dc826b +size 4321962688 diff --git a/CataLlama-v0.1-Base.Q3_K_M.gguf b/CataLlama-v0.1-Base.Q3_K_M.gguf new file mode 100644 index 0000000..801d62f --- /dev/null +++ b/CataLlama-v0.1-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61e6f19860e700125092c7aeaea136f22f7e26d390069d0778378ce991fee220 +size 4018924224 diff --git a/CataLlama-v0.1-Base.Q3_K_S.gguf b/CataLlama-v0.1-Base.Q3_K_S.gguf new file mode 100644 index 0000000..5858b33 --- /dev/null +++ b/CataLlama-v0.1-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:414a1e24c0a634792406946549fb74562e62f52829779925b1c5bd1ed0fc0147 +size 3664505536 diff --git a/CataLlama-v0.1-Base.Q4_K_M.gguf b/CataLlama-v0.1-Base.Q4_K_M.gguf new file mode 100644 index 0000000..6956d50 --- /dev/null +++ b/CataLlama-v0.1-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce43f265b3219206e1cf77691fa0b6fdccfe73d2057846cb0e1838105fb7e16 +size 4920741088 diff --git a/CataLlama-v0.1-Base.Q4_K_S.gguf b/CataLlama-v0.1-Base.Q4_K_S.gguf new file mode 100644 index 0000000..7e3795b --- /dev/null +++ b/CataLlama-v0.1-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:559fc5484406d1710056025849b1dd54f684369c8e46732fba9c007c998a13ea +size 4692675808 diff --git a/CataLlama-v0.1-Base.Q5_K_M.gguf b/CataLlama-v0.1-Base.Q5_K_M.gguf new file mode 100644 index 0000000..6218fdb --- /dev/null +++ b/CataLlama-v0.1-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9470e795efa1a0899e76049cc6485a5bb545d85c826aa404c46db050d542efb2 +size 5732994784 diff --git a/CataLlama-v0.1-Base.Q5_K_S.gguf b/CataLlama-v0.1-Base.Q5_K_S.gguf new file mode 100644 index 0000000..da96fed --- /dev/null +++ b/CataLlama-v0.1-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b69eb8d18674077a1c6fb9bb60c17b4dc41bf310d532d41389138557086a2d +size 5599301344 diff --git a/CataLlama-v0.1-Base.Q6_K.gguf b/CataLlama-v0.1-Base.Q6_K.gguf new file mode 100644 index 0000000..52f4987 --- /dev/null +++ b/CataLlama-v0.1-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e05a74297478218ecc86c59031c49e63dcbea5dfa84bde20fd816af6a675e036 +size 6596014336 diff --git a/CataLlama-v0.1-Base.Q8_0.gguf b/CataLlama-v0.1-Base.Q8_0.gguf new file mode 100644 index 0000000..da05387 --- /dev/null +++ b/CataLlama-v0.1-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372bbef80617bc487085ad509db92cf8acb25d123f8362f5650ac8207e5e7ee9 +size 8540780736 diff --git a/CataLlama-v0.1-Base.f16.gguf b/CataLlama-v0.1-Base.f16.gguf new file mode 100644 index 0000000..c63486d --- /dev/null +++ b/CataLlama-v0.1-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d8a731272042f0d9629411a6b3aa7643db3a320e59864d462b38e6542160df +size 16068908736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..abf88a7 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: catallama/CataLlama-v0.1-Base +datasets: +- catallama/Catalan-Raw-Text +language: +- ca +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- llama-3 +- Catalan +--- +## About + + + + + + +static quants of https://huggingface.co/catallama/CataLlama-v0.1-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CataLlama-v0.1-Base-GGUF).*** + +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-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-Base.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CataLlama-v0.1-Base-GGUF/resolve/main/CataLlama-v0.1-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. + +