commit 449c90583374cd27a53734d1d44cbcfedc2a4665 Author: ModelHub XC Date: Sat Aug 15 10:35:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..49c8801 --- /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-3.1-Lafaek-8B-v5.1-91.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Lafaek-8B-v5.1-91.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.IQ4_XS.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.IQ4_XS.gguf new file mode 100644 index 0000000..f4ee9e5 --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fe5cddfcf4d3ff6d679d70f3660388ced0335597726a0d57215e87157d9d0ca +size 4484363808 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q2_K.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q2_K.gguf new file mode 100644 index 0000000..f75cfd8 --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d649c9d1f15760035115f46759c492a0ac79e9a3ba77954d44116462ba3ee51 +size 3179132448 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_L.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_L.gguf new file mode 100644 index 0000000..875dff9 --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b1ec11b3c9c78c0ef12a8b465ffb522ac37473de456dbe5d11cf5e3b495255 +size 4321957408 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_M.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_M.gguf new file mode 100644 index 0000000..412e9f9 --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8519f51adf2ee38274a1318e317a2d8e81d3c8fce4f8d584c23f04e014e91bdc +size 4018918944 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_S.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_S.gguf new file mode 100644 index 0000000..fbf957d --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:068bb88a7ca145b565e6f9bfb2f102a70300b2d869c3afb5e57d2ba43b0526b3 +size 3664500256 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_M.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_M.gguf new file mode 100644 index 0000000..205e6fa --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c7554a6975d0fdc2f33c858638f9b15fad17adf21e5fb20c492ed6ae3a5f04 +size 4920735264 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_S.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_S.gguf new file mode 100644 index 0000000..5fb1192 --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c93e9d9a47da74f6ab8a29ed2e46493e149e1d4d9c4fe4110a3e04d3764901a +size 4692669984 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_M.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_M.gguf new file mode 100644 index 0000000..efde469 --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed5f73b3836d380405154d6522e013bec975835bd603be6db1366648cb827c85 +size 5732988448 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_S.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_S.gguf new file mode 100644 index 0000000..08bd72f --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7ba095c2e7288600c375d7fd6c2d75a9b4df04420039b7a0fa47f38b5e7206 +size 5599295008 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q6_K.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q6_K.gguf new file mode 100644 index 0000000..7dcbacb --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c9cb2204ff973e56a62a311c66792aead6bbbbc27e5d79411f10151376e3175 +size 6596007456 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.Q8_0.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.Q8_0.gguf new file mode 100644 index 0000000..76b5a4c --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b040c0f7eba4ec594972ffdc93c89c4ca355b271601eb8738741905e0c3047e8 +size 8540771872 diff --git a/Llama-3.1-Lafaek-8B-v5.1-91.f16.gguf b/Llama-3.1-Lafaek-8B-v5.1-91.f16.gguf new file mode 100644 index 0000000..dc27b41 --- /dev/null +++ b/Llama-3.1-Lafaek-8B-v5.1-91.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca10b1231545a675f66e3105e2d9f5141f34f5cdc1bad440029dac4f7f850a2 +size 16068892192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8eaf15b --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Yuichi1218/Llama-3.1-Lafaek-8B-v5.1-91 +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/Llama-3.1-Lafaek-8B-v5.1-91 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-Lafaek-8B-v5.1-91-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-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Lafaek-8B-v5.1-91-GGUF/resolve/main/Llama-3.1-Lafaek-8B-v5.1-91.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. + +