commit af4b2b919f7f7d3f44925e6f68a7e7a22f363bb4 Author: ModelHub XC Date: Fri Sep 18 02:12:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Lugha-Llama-8B-wura-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..96c7ef7 --- /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 +Lugha-Llama-8B-wura.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Lugha-Llama-8B-wura.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Lugha-Llama-8B-wura.IQ4_XS.gguf b/Lugha-Llama-8B-wura.IQ4_XS.gguf new file mode 100644 index 0000000..b34919f --- /dev/null +++ b/Lugha-Llama-8B-wura.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4574717ff85ba330a09a860c70899fe6a03660e79d67bb96501faada4a734f16 +size 4484367360 diff --git a/Lugha-Llama-8B-wura.Q2_K.gguf b/Lugha-Llama-8B-wura.Q2_K.gguf new file mode 100644 index 0000000..f8bd48c --- /dev/null +++ b/Lugha-Llama-8B-wura.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9227d43e4aceba0d856a6b9d61f69baea636e9e41d953f3e5567f6e0d1eb20 +size 3179136000 diff --git a/Lugha-Llama-8B-wura.Q3_K_L.gguf b/Lugha-Llama-8B-wura.Q3_K_L.gguf new file mode 100644 index 0000000..35c822c --- /dev/null +++ b/Lugha-Llama-8B-wura.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e1d55101da2dddb55b4e90bdc892cc4a8ff90ac049f877462be264d9be12e1 +size 4321960960 diff --git a/Lugha-Llama-8B-wura.Q3_K_M.gguf b/Lugha-Llama-8B-wura.Q3_K_M.gguf new file mode 100644 index 0000000..9446444 --- /dev/null +++ b/Lugha-Llama-8B-wura.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14fb379361df407e39021f014dbffd7d701837d475815e8a5c26671175d31e85 +size 4018922496 diff --git a/Lugha-Llama-8B-wura.Q3_K_S.gguf b/Lugha-Llama-8B-wura.Q3_K_S.gguf new file mode 100644 index 0000000..ae8ced4 --- /dev/null +++ b/Lugha-Llama-8B-wura.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b4020550c243e2b832fe53bbd6f21a5055dd18233c6309b3141bad7d03ebc4 +size 3664503808 diff --git a/Lugha-Llama-8B-wura.Q4_K_M.gguf b/Lugha-Llama-8B-wura.Q4_K_M.gguf new file mode 100644 index 0000000..e72e06b --- /dev/null +++ b/Lugha-Llama-8B-wura.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8aeb7fafcf2d3f4a1941581a9d652fee348e0e657627ee6f0e9b2339c9e65b +size 4920738816 diff --git a/Lugha-Llama-8B-wura.Q4_K_S.gguf b/Lugha-Llama-8B-wura.Q4_K_S.gguf new file mode 100644 index 0000000..c6da8fc --- /dev/null +++ b/Lugha-Llama-8B-wura.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d163a9c7d571985e068254fa750093c578b866844e98ee3f65d729e0c155c4d2 +size 4692673536 diff --git a/Lugha-Llama-8B-wura.Q5_K_M.gguf b/Lugha-Llama-8B-wura.Q5_K_M.gguf new file mode 100644 index 0000000..23e07f2 --- /dev/null +++ b/Lugha-Llama-8B-wura.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc222888c96e13e79e021c9ccfc110b0418742c4a2179aa6889686f129c09856 +size 5732992000 diff --git a/Lugha-Llama-8B-wura.Q5_K_S.gguf b/Lugha-Llama-8B-wura.Q5_K_S.gguf new file mode 100644 index 0000000..17be8e4 --- /dev/null +++ b/Lugha-Llama-8B-wura.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58598d250811bd46682d431fe6121659df2c6dff5aeb143269cbd035ee6fc6ea +size 5599298560 diff --git a/Lugha-Llama-8B-wura.Q6_K.gguf b/Lugha-Llama-8B-wura.Q6_K.gguf new file mode 100644 index 0000000..cd67cc4 --- /dev/null +++ b/Lugha-Llama-8B-wura.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8bbd4bb891bfaec31fadfee0ba630b73b931a02d428d858f4296efa28173a8e +size 6596011008 diff --git a/Lugha-Llama-8B-wura.Q8_0.gguf b/Lugha-Llama-8B-wura.Q8_0.gguf new file mode 100644 index 0000000..b4fd523 --- /dev/null +++ b/Lugha-Llama-8B-wura.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed6a61806763959bca1ff7754aa3ff6662715f84c1bb15ada1f04c0c7d81b92 +size 8540775424 diff --git a/Lugha-Llama-8B-wura.f16.gguf b/Lugha-Llama-8B-wura.f16.gguf new file mode 100644 index 0000000..a53d72d --- /dev/null +++ b/Lugha-Llama-8B-wura.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3dd83a8fe3f82399e00fa3f1ae5f0ce4b590015ae9eed581af589e543079da6 +size 16068895744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d7cf260 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Lugha-Models/Lugha-Llama-8B-wura +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/Lugha-Models/Lugha-Llama-8B-wura + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Lugha-Llama-8B-wura-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-i1-GGUF +## 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/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Lugha-Llama-8B-wura-GGUF/resolve/main/Lugha-Llama-8B-wura.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. + +