commit 569b1319f62ead5622339dd22b060c92446a3ab6 Author: ModelHub XC Date: Tue Aug 4 02:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-LoyalLizard-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2df7b32 --- /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 +Llama3.1-LoyalLizard-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-LoyalLizard-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-LoyalLizard-8B.IQ4_XS.gguf b/Llama3.1-LoyalLizard-8B.IQ4_XS.gguf new file mode 100644 index 0000000..c1a7c77 --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:226569eff491efe73b6c048eeccbe53e01be1a3f3745c2a310aad4001412174c +size 4484364192 diff --git a/Llama3.1-LoyalLizard-8B.Q2_K.gguf b/Llama3.1-LoyalLizard-8B.Q2_K.gguf new file mode 100644 index 0000000..c71f858 --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0eccb22f91361d27fcb698e3117eecf8a8ec151b109459aa13867028bebae1 +size 3179132832 diff --git a/Llama3.1-LoyalLizard-8B.Q3_K_L.gguf b/Llama3.1-LoyalLizard-8B.Q3_K_L.gguf new file mode 100644 index 0000000..64d88c5 --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92b375c09224a549a53da72178fbf49945421871d4678aadd4f5334800c7d0b +size 4321957792 diff --git a/Llama3.1-LoyalLizard-8B.Q3_K_M.gguf b/Llama3.1-LoyalLizard-8B.Q3_K_M.gguf new file mode 100644 index 0000000..8484171 --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f75a68a7df77595b2bdee33b4a54b0787759936451a95bdbbb05d3e9334024a +size 4018919328 diff --git a/Llama3.1-LoyalLizard-8B.Q3_K_S.gguf b/Llama3.1-LoyalLizard-8B.Q3_K_S.gguf new file mode 100644 index 0000000..3dd17dd --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cae2846415a80ba83678584d4e36fc05eaf32937e931799d57cebf6696806d78 +size 3664500640 diff --git a/Llama3.1-LoyalLizard-8B.Q4_K_M.gguf b/Llama3.1-LoyalLizard-8B.Q4_K_M.gguf new file mode 100644 index 0000000..55423e8 --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c61ed0382c0052d074e326fc8ee3a7105caccd549a0c69db4697ff6ab56dd8d +size 4920735648 diff --git a/Llama3.1-LoyalLizard-8B.Q4_K_S.gguf b/Llama3.1-LoyalLizard-8B.Q4_K_S.gguf new file mode 100644 index 0000000..bbf8717 --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cad894c36316e2f23f80f1d40691461ef20f2e7d99b6ff08b982a4706d96156 +size 4692670368 diff --git a/Llama3.1-LoyalLizard-8B.Q5_K_M.gguf b/Llama3.1-LoyalLizard-8B.Q5_K_M.gguf new file mode 100644 index 0000000..c5f4db1 --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4985f82eab7b07717c6b1882677457145132e79b8b4a60fbbe083c21fc2ec04a +size 5732988832 diff --git a/Llama3.1-LoyalLizard-8B.Q5_K_S.gguf b/Llama3.1-LoyalLizard-8B.Q5_K_S.gguf new file mode 100644 index 0000000..b2b2027 --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:353068d2d29ab462ccfe7431f67cf39605f4f8e4d3b631042ac05a1f9e22eba4 +size 5599295392 diff --git a/Llama3.1-LoyalLizard-8B.Q6_K.gguf b/Llama3.1-LoyalLizard-8B.Q6_K.gguf new file mode 100644 index 0000000..4edee39 --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4196df9062b3058e86c87d9daad6ea69e90a5b1fba5ff91f30a7a71b27ecb904 +size 6596007840 diff --git a/Llama3.1-LoyalLizard-8B.Q8_0.gguf b/Llama3.1-LoyalLizard-8B.Q8_0.gguf new file mode 100644 index 0000000..7d5beba --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd17f001fe6f9a692d7c2283abfe8918bdae104f5e91f51e84daea79836259c0 +size 8540772256 diff --git a/Llama3.1-LoyalLizard-8B.f16.gguf b/Llama3.1-LoyalLizard-8B.f16.gguf new file mode 100644 index 0000000..489aafd --- /dev/null +++ b/Llama3.1-LoyalLizard-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31abb9bcd09bd4e5ac70b3e4a3dab52f33b5f742b0d8fe6c7d40a3e01c97efa +size 16068892576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1c94049 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Yuma42/Llama3.1-LoyalLizard-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- Yuma42/Llama3.1-IgneousIguana-8B +- vicgalle/Configurable-Llama-3.1-8B-Instruct +--- +## About + + + + + + +static quants of https://huggingface.co/Yuma42/Llama3.1-LoyalLizard-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-LoyalLizard-8B-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/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-LoyalLizard-8B-GGUF/resolve/main/Llama3.1-LoyalLizard-8B.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. + +