From d4d9d128cfc44bc88278847a5b36cdcd6b1c2338 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 18 Oct 2026 02:39:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF Source: Original Platform --- .gitattributes | 50 +++++++++++++++++ Llama-3.1-8B-Instuct-Uz.IQ3_M.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.IQ3_S.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.IQ3_XS.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.IQ4_XS.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q2_K.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q3_K_L.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q3_K_M.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q3_K_S.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q4_K_M.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q4_K_S.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q5_K_M.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q5_K_S.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q6_K.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.Q8_0.gguf | 3 ++ Llama-3.1-8B-Instuct-Uz.f16.gguf | 3 ++ README.md | 83 +++++++++++++++++++++++++++++ 17 files changed, 178 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama-3.1-8B-Instuct-Uz.IQ3_M.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.IQ3_S.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.IQ3_XS.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.IQ4_XS.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q2_K.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q3_K_L.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q3_K_M.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q3_K_S.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q4_K_M.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q4_K_S.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q5_K_M.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q5_K_S.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q6_K.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.Q8_0.gguf create mode 100644 Llama-3.1-8B-Instuct-Uz.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b34e457 --- /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 +Llama-3.1-8B-Instuct-Uz.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instuct-Uz.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Instuct-Uz.IQ3_M.gguf b/Llama-3.1-8B-Instuct-Uz.IQ3_M.gguf new file mode 100644 index 0000000..e74f41b --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88e3d587d978f6ada89a562f05a5b5d8d3ed32361dbc87d4be8dbddc1e8cd97f +size 3784824896 diff --git a/Llama-3.1-8B-Instuct-Uz.IQ3_S.gguf b/Llama-3.1-8B-Instuct-Uz.IQ3_S.gguf new file mode 100644 index 0000000..dbc59c3 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c29244c3406b5803cb0c8ac727d7c5728737890607118b2695f1036ba35b02 +size 3682326592 diff --git a/Llama-3.1-8B-Instuct-Uz.IQ3_XS.gguf b/Llama-3.1-8B-Instuct-Uz.IQ3_XS.gguf new file mode 100644 index 0000000..fe4615a --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b992d22f1d469864e153757ecb1a150807c65c37d331bc9dafd60d9f83b786ba +size 3518748736 diff --git a/Llama-3.1-8B-Instuct-Uz.IQ4_XS.gguf b/Llama-3.1-8B-Instuct-Uz.IQ4_XS.gguf new file mode 100644 index 0000000..8e5a7a8 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d913a3e925914f3dddcd82d930fb9c1f29b8298ea98ca5a2f3c92d174a2e8154 +size 4484364352 diff --git a/Llama-3.1-8B-Instuct-Uz.Q2_K.gguf b/Llama-3.1-8B-Instuct-Uz.Q2_K.gguf new file mode 100644 index 0000000..5f25a44 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa3aec42a0c09b3ad5c0a01771ccc53b27d7ddb48714a83b40274891a3fc82fc +size 3179132992 diff --git a/Llama-3.1-8B-Instuct-Uz.Q3_K_L.gguf b/Llama-3.1-8B-Instuct-Uz.Q3_K_L.gguf new file mode 100644 index 0000000..d3889b7 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:120052a1608c3441c360ab5ee51073035e4cec4af391dec6ba1ae292a1bbb444 +size 4321957952 diff --git a/Llama-3.1-8B-Instuct-Uz.Q3_K_M.gguf b/Llama-3.1-8B-Instuct-Uz.Q3_K_M.gguf new file mode 100644 index 0000000..1b5d2bc --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b93191d9c737f42c63892faf7853da24e9364573b225c269e575c2e704a3707 +size 4018919488 diff --git a/Llama-3.1-8B-Instuct-Uz.Q3_K_S.gguf b/Llama-3.1-8B-Instuct-Uz.Q3_K_S.gguf new file mode 100644 index 0000000..4ef6b12 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c649177ef8b22a57ef2755daf00ee0addd0ebcadc3091910274093df88fbcf5d +size 3664500800 diff --git a/Llama-3.1-8B-Instuct-Uz.Q4_K_M.gguf b/Llama-3.1-8B-Instuct-Uz.Q4_K_M.gguf new file mode 100644 index 0000000..e1c2049 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9faf8e555b8083704f48f36504f3ee8e89a9e6f6877970a5a5772f08d22d1471 +size 4920735808 diff --git a/Llama-3.1-8B-Instuct-Uz.Q4_K_S.gguf b/Llama-3.1-8B-Instuct-Uz.Q4_K_S.gguf new file mode 100644 index 0000000..11a9aa9 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d98ce8348316e68e0c4ef23b67fea7ace547bf80aa469e282d22632c49b176a8 +size 4692670528 diff --git a/Llama-3.1-8B-Instuct-Uz.Q5_K_M.gguf b/Llama-3.1-8B-Instuct-Uz.Q5_K_M.gguf new file mode 100644 index 0000000..4c35c49 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c70257aeb541c54794b10430669b4224671dd35cbcd89c4203dc4383f39668 +size 5732988992 diff --git a/Llama-3.1-8B-Instuct-Uz.Q5_K_S.gguf b/Llama-3.1-8B-Instuct-Uz.Q5_K_S.gguf new file mode 100644 index 0000000..48fce98 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61ffca50f7fc8a4d70998cc435587cb089234d200d683967897819c2d82ba6b +size 5599295552 diff --git a/Llama-3.1-8B-Instuct-Uz.Q6_K.gguf b/Llama-3.1-8B-Instuct-Uz.Q6_K.gguf new file mode 100644 index 0000000..1fed220 --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce46d34bd77cd0dd024819ea01f5a3dc2ffbd129ec27afb6ce9e0b65ef9788da +size 6596008000 diff --git a/Llama-3.1-8B-Instuct-Uz.Q8_0.gguf b/Llama-3.1-8B-Instuct-Uz.Q8_0.gguf new file mode 100644 index 0000000..89d2d7b --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca103611fda76157d3f81657114cd83ebf9d35fe3405e25953ce958e4e967cd9 +size 8540772416 diff --git a/Llama-3.1-8B-Instuct-Uz.f16.gguf b/Llama-3.1-8B-Instuct-Uz.f16.gguf new file mode 100644 index 0000000..caac7aa --- /dev/null +++ b/Llama-3.1-8B-Instuct-Uz.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3e76bd2d63ef5b1ccdd25b2866ace832c20dbb6c6d19653e633df72a4dafdad +size 16068892736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c7ec06d --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: behbudiy/Llama-3.1-8B-Instruct-Uz +datasets: +- yahma/alpaca-cleaned +- behbudiy/alpaca-cleaned-uz +- behbudiy/translation-instruction +language: +- uz +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- text-generation-inference +- summarization +- translation +- question-answering +--- +## About + + + + + + +static quants of https://huggingface.co/behbudiy/Llama-3.1-8B-Instruct-Uz + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-8B-Instuct-Uz-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-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF/resolve/main/Llama-3.1-8B-Instuct-Uz.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. + +