commit 820555fa4c5b0eb6ce6c6c2b13a657ee75961d1f Author: ModelHub XC Date: Sun Sep 6 22:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2ad514f --- /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 +Lafaek-Llama-3.1-8B-Xmas.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.f16.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Lafaek-Llama-3.1-8B-Xmas.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Lafaek-Llama-3.1-8B-Xmas.IQ4_XS.gguf b/Lafaek-Llama-3.1-8B-Xmas.IQ4_XS.gguf new file mode 100644 index 0000000..3a1b8df --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e94c10b43c11805d2a4831aa97294fe74b8639fda012ef09359d4bff140bf7f +size 4484363776 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q2_K.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q2_K.gguf new file mode 100644 index 0000000..9418a86 --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b3309a0541a4a4d1c8e884a2b16915e5a66b63b0bbad97d7d7232dd6abec6f +size 3179132416 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q3_K_L.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q3_K_L.gguf new file mode 100644 index 0000000..6c4ae95 --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d10aea3fafe4f70756fdf3994e3f2b8f8bc98def6d8d77347355be66551bb81 +size 4321957376 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q3_K_M.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q3_K_M.gguf new file mode 100644 index 0000000..26a6c88 --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1ab449a35e843fedf263169bdfd33c7ab97a99eb08f94bf7e278b465472724 +size 4018918912 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q3_K_S.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q3_K_S.gguf new file mode 100644 index 0000000..3ec0ad1 --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f66bb8081bd1561c814da9e00896e152e534c877ee9c18f97a6a2fadb73ef6f +size 3664500224 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q4_K_M.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q4_K_M.gguf new file mode 100644 index 0000000..60e5969 --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb88ed0a190d06bf10fa94c85a67c4fb1f8458de8d90f60113e4a4c9351266f +size 4920735232 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q4_K_S.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q4_K_S.gguf new file mode 100644 index 0000000..69331ab --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc8488d734a574c115a9baa198ce66e9212652853c24a8428f79ad7c1ab4215a +size 4692669952 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q5_K_M.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q5_K_M.gguf new file mode 100644 index 0000000..61771a2 --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29b33f82ee7af29e5049f20980cb12ec6663279b0cfc3eda43e3cfa8b5a357a7 +size 5732988416 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q5_K_S.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q5_K_S.gguf new file mode 100644 index 0000000..934965b --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109a364c23d9613ffa3384521ae728026f93f782e3fcfbbe432103825915cbec +size 5599294976 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q6_K.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q6_K.gguf new file mode 100644 index 0000000..083510d --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45986bd7603d2a00c76be7afac9f82839f3eb6a6f53165aeb7b4ab631df2cc11 +size 6596007424 diff --git a/Lafaek-Llama-3.1-8B-Xmas.Q8_0.gguf b/Lafaek-Llama-3.1-8B-Xmas.Q8_0.gguf new file mode 100644 index 0000000..56f886f --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:004d20716a91c4091e098776d44ecb528559e7adb60da48c7e51d776b578b27f +size 8540771840 diff --git a/Lafaek-Llama-3.1-8B-Xmas.f16.gguf b/Lafaek-Llama-3.1-8B-Xmas.f16.gguf new file mode 100644 index 0000000..1e14f2a --- /dev/null +++ b/Lafaek-Llama-3.1-8B-Xmas.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1811b2451613cf21d9879e31212ee9f5c1ce09873a2c5e9ecf0ddb036871a156 +size 16068892160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a03046 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Yuichi1218/Lafaek-Llama-3.1-8B-Xmas +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Yuichi1218/Lafaek-Llama-3.1-8B-Xmas + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Lafaek-Llama-3.1-8B-Xmas-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-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/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Lafaek-Llama-3.1-8B-Xmas-GGUF/resolve/main/Lafaek-Llama-3.1-8B-Xmas.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. + +