commit 478e3e085779b8c9a21f62a033c34815283ff8df Author: ModelHub XC Date: Thu Jul 23 16:12:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlamaUz-3.1-8b-ct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e4d9648 --- /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 +LlamaUz-3.1-8b-ct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LlamaUz-3.1-8b-ct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlamaUz-3.1-8b-ct.IQ4_XS.gguf b/LlamaUz-3.1-8b-ct.IQ4_XS.gguf new file mode 100644 index 0000000..8810edc --- /dev/null +++ b/LlamaUz-3.1-8b-ct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb7c6dc7a80771530946459027bc063510811c3510cec2fdfd27d3a6571b7dd +size 4484363712 diff --git a/LlamaUz-3.1-8b-ct.Q2_K.gguf b/LlamaUz-3.1-8b-ct.Q2_K.gguf new file mode 100644 index 0000000..1d7a858 --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1871fb12b0d8e01a02b998ea0d0bb6e32a0fe302e2318c237f9c9824e493ad +size 3179132352 diff --git a/LlamaUz-3.1-8b-ct.Q3_K_L.gguf b/LlamaUz-3.1-8b-ct.Q3_K_L.gguf new file mode 100644 index 0000000..1cdda5f --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de9b357498f3c81be541205e5f8faf709f422eecbc7fd285161f24bc279a492 +size 4321957312 diff --git a/LlamaUz-3.1-8b-ct.Q3_K_M.gguf b/LlamaUz-3.1-8b-ct.Q3_K_M.gguf new file mode 100644 index 0000000..703d42d --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e483cda42cc74cd7c0f96f6fc65d087e13bbdd14c1ed3cd03d8bffe2ad0a151 +size 4018918848 diff --git a/LlamaUz-3.1-8b-ct.Q3_K_S.gguf b/LlamaUz-3.1-8b-ct.Q3_K_S.gguf new file mode 100644 index 0000000..6f3d28c --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5626375d94e0f78194d7633a13b6a8672e1f413d98496894d226fc25c9307265 +size 3664500160 diff --git a/LlamaUz-3.1-8b-ct.Q4_K_M.gguf b/LlamaUz-3.1-8b-ct.Q4_K_M.gguf new file mode 100644 index 0000000..652d19b --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a81c131682557b494aba1dc8bf967c56eafe16b9c7a2bd129ac63b7ee6e8cbb4 +size 4920735168 diff --git a/LlamaUz-3.1-8b-ct.Q4_K_S.gguf b/LlamaUz-3.1-8b-ct.Q4_K_S.gguf new file mode 100644 index 0000000..0330eb6 --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4bcbf0a4c762504374f99a0c6798c602f24164860f00a70f0b4c34639113776 +size 4692669888 diff --git a/LlamaUz-3.1-8b-ct.Q5_K_M.gguf b/LlamaUz-3.1-8b-ct.Q5_K_M.gguf new file mode 100644 index 0000000..9cdda17 --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69004d8b9b541f546a27b3ee86eaa44224a90847e3a6807e5395aca90ace417 +size 5732988352 diff --git a/LlamaUz-3.1-8b-ct.Q5_K_S.gguf b/LlamaUz-3.1-8b-ct.Q5_K_S.gguf new file mode 100644 index 0000000..93216ca --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560bd6dd20f661e4cd66f59bbfb50e3c20504c9193ad6da1f67a659a44fd80f9 +size 5599294912 diff --git a/LlamaUz-3.1-8b-ct.Q6_K.gguf b/LlamaUz-3.1-8b-ct.Q6_K.gguf new file mode 100644 index 0000000..67e2d93 --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fee0617f98fc53550c41d4a16f3088c2b462b534535031b4581a1ace86f17ec1 +size 6596007360 diff --git a/LlamaUz-3.1-8b-ct.Q8_0.gguf b/LlamaUz-3.1-8b-ct.Q8_0.gguf new file mode 100644 index 0000000..e854402 --- /dev/null +++ b/LlamaUz-3.1-8b-ct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b323a5cee39527f5a1f59460496d086b92173fc1cf048d40a327b3121290d01d +size 8540771776 diff --git a/LlamaUz-3.1-8b-ct.f16.gguf b/LlamaUz-3.1-8b-ct.f16.gguf new file mode 100644 index 0000000..546c97b --- /dev/null +++ b/LlamaUz-3.1-8b-ct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb5d073b0328340bf082562c2ebd1ae3615dab5c660b3a1a34a470b9ac5759ca +size 16068892096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c58c9c9 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: IzzatilloAI/LlamaUz-3.1-8b-ct +datasets: +- wikimedia/wikipedia +language: +- uz +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/IzzatilloAI/LlamaUz-3.1-8b-ct + + +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/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaUz-3.1-8b-ct-GGUF/resolve/main/LlamaUz-3.1-8b-ct.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. + +