commit 438bd9a7c4d89904d9193e17b34983f7c52cc96c Author: ModelHub XC Date: Sat May 30 21:56:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-mono-Basque-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..267e91b --- /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 +Llama-3-8B-mono-Basque.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-mono-Basque.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-mono-Basque.IQ4_XS.gguf b/Llama-3-8B-mono-Basque.IQ4_XS.gguf new file mode 100644 index 0000000..74331fe --- /dev/null +++ b/Llama-3-8B-mono-Basque.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df89c1b7f7028376075be2557a8c4f54f5a5ce80c11173e42dae4d2653cc569d +size 4484363200 diff --git a/Llama-3-8B-mono-Basque.Q2_K.gguf b/Llama-3-8B-mono-Basque.Q2_K.gguf new file mode 100644 index 0000000..01118bb --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:279322c43f8350740fcc47b66ca579e9ddd0a762da2b02a17b599ded17d39b6c +size 3179131840 diff --git a/Llama-3-8B-mono-Basque.Q3_K_L.gguf b/Llama-3-8B-mono-Basque.Q3_K_L.gguf new file mode 100644 index 0000000..b4edae0 --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77336faf59335eaca83f61dd92bb4b6c4eb66722a58e9f14165eaab74cc60be6 +size 4321956800 diff --git a/Llama-3-8B-mono-Basque.Q3_K_M.gguf b/Llama-3-8B-mono-Basque.Q3_K_M.gguf new file mode 100644 index 0000000..0b0dd00 --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc1ebb556cb0005d95f537dab299f9eed81b0eed691ce8b399c2e16bd82b025 +size 4018918336 diff --git a/Llama-3-8B-mono-Basque.Q3_K_S.gguf b/Llama-3-8B-mono-Basque.Q3_K_S.gguf new file mode 100644 index 0000000..79301a3 --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee1a90172be46003c074e35738347e9dfe61e2cc9fb19f12030936e76ebb6607 +size 3664499648 diff --git a/Llama-3-8B-mono-Basque.Q4_K_M.gguf b/Llama-3-8B-mono-Basque.Q4_K_M.gguf new file mode 100644 index 0000000..9f30c26 --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ac15c18fe9e756262ae02033e30ea3c449f08b25daf6cf6a4e69f6886349ae +size 4920734656 diff --git a/Llama-3-8B-mono-Basque.Q4_K_S.gguf b/Llama-3-8B-mono-Basque.Q4_K_S.gguf new file mode 100644 index 0000000..b391656 --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb8e8dac760242a01bda1f737c5dc0a0443b2d2120ffde085006ff1f5262d04 +size 4692669376 diff --git a/Llama-3-8B-mono-Basque.Q5_K_M.gguf b/Llama-3-8B-mono-Basque.Q5_K_M.gguf new file mode 100644 index 0000000..59b02a4 --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0dc76dcc4456efa82f732128c8c40daa855669f5b03223e4b51f2bbc9ff6cfe +size 5732987840 diff --git a/Llama-3-8B-mono-Basque.Q5_K_S.gguf b/Llama-3-8B-mono-Basque.Q5_K_S.gguf new file mode 100644 index 0000000..812ac5f --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c429bbb2f0b7c3ec6bc6c21ca845433655d374c136f0fc49fb3ffe8e0ccdbe +size 5599294400 diff --git a/Llama-3-8B-mono-Basque.Q6_K.gguf b/Llama-3-8B-mono-Basque.Q6_K.gguf new file mode 100644 index 0000000..2f557ed --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10afdb522a1dd7b04292bed7d9396d4deb211662435bfbacb47692009b4fd195 +size 6596006848 diff --git a/Llama-3-8B-mono-Basque.Q8_0.gguf b/Llama-3-8B-mono-Basque.Q8_0.gguf new file mode 100644 index 0000000..f421054 --- /dev/null +++ b/Llama-3-8B-mono-Basque.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcb501e8ec24263be9d5f208622af0cfbd94dee998593fb777588a4f0e273f4b +size 8540771264 diff --git a/Llama-3-8B-mono-Basque.f16.gguf b/Llama-3-8B-mono-Basque.f16.gguf new file mode 100644 index 0000000..904d4a8 --- /dev/null +++ b/Llama-3-8B-mono-Basque.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45a27bcf7d714b774b31c3c41f2ea6ad821d2b5aca0681637ba48808db6e0c8a +size 16068891584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a698bf4 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: almanach/Llama-3-8B-mono-Basque +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/almanach/Llama-3-8B-mono-Basque + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-8B-mono-Basque-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/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-mono-Basque-GGUF/resolve/main/Llama-3-8B-mono-Basque.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. + +