commit 38081778d75c0c76700768525ef8caa565f0b94e Author: ModelHub XC Date: Sat Jul 11 11:10:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Lunar-8B-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7f63ae4 --- /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-Lunar-8B-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Lunar-8B-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Lunar-8B-v0.1.IQ4_XS.gguf b/Llama-3-Lunar-8B-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..e342a63 --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c3dc493054d7de285bda2f252f01adbf367c6c55ec6eab68fccfa5d4fe2bcd +size 4484362816 diff --git a/Llama-3-Lunar-8B-v0.1.Q2_K.gguf b/Llama-3-Lunar-8B-v0.1.Q2_K.gguf new file mode 100644 index 0000000..656881c --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f32fe7e7f4df6f8ffb68b8c1e26c59d925e84c145237ab57d446a0c17b5f1ba +size 3179131456 diff --git a/Llama-3-Lunar-8B-v0.1.Q3_K_L.gguf b/Llama-3-Lunar-8B-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..800085c --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a357e9d21d7d2679af155de3c06e3f1cfc3db5f53bc0cfdc8ba98ae5265101e +size 4321956416 diff --git a/Llama-3-Lunar-8B-v0.1.Q3_K_M.gguf b/Llama-3-Lunar-8B-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..2dff8fb --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d37243a4ba014317e78baafba356b57ce52fe1d3358e42a8ed5aba33564538a +size 4018917952 diff --git a/Llama-3-Lunar-8B-v0.1.Q3_K_S.gguf b/Llama-3-Lunar-8B-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..35b5ccc --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6266e2ab5e7881e0b19287545105a6d84127b939ce422054d365c6881eaac7 +size 3664499264 diff --git a/Llama-3-Lunar-8B-v0.1.Q4_K_M.gguf b/Llama-3-Lunar-8B-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..5adc5da --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a3a381399340b70816ccc1097cd95d3e747a69b9b967c3cbc0d07d484870c39 +size 4920734272 diff --git a/Llama-3-Lunar-8B-v0.1.Q4_K_S.gguf b/Llama-3-Lunar-8B-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..020112f --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63373761b3c0c69bbbb2df05e1511ff7dfb3d02b0a0da9b273144ae82520eec2 +size 4692668992 diff --git a/Llama-3-Lunar-8B-v0.1.Q5_K_M.gguf b/Llama-3-Lunar-8B-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..2a3a19f --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e779d719d691d086577762b3e2c9d2ef6517fba6f5a4fcf779301be59c73c0b4 +size 5732987456 diff --git a/Llama-3-Lunar-8B-v0.1.Q5_K_S.gguf b/Llama-3-Lunar-8B-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..c1cf3ce --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58409fa73d8b1917b1727528299d24d43c19be61ece3fd40c39e343fcf7ccaa +size 5599294016 diff --git a/Llama-3-Lunar-8B-v0.1.Q6_K.gguf b/Llama-3-Lunar-8B-v0.1.Q6_K.gguf new file mode 100644 index 0000000..f73a2df --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef109591ea436671f8cbe37b5db1548c3287fc61dd7d3bcf31863cbdcac9bde1 +size 6596006464 diff --git a/Llama-3-Lunar-8B-v0.1.Q8_0.gguf b/Llama-3-Lunar-8B-v0.1.Q8_0.gguf new file mode 100644 index 0000000..b75193a --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5952f58ff6ac8cdaa0995cc7a7726467ac93498fd2206693c67142f2f9c42b8 +size 8540770880 diff --git a/Llama-3-Lunar-8B-v0.1.f16.gguf b/Llama-3-Lunar-8B-v0.1.f16.gguf new file mode 100644 index 0000000..4714d8b --- /dev/null +++ b/Llama-3-Lunar-8B-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24442bda653d84952b256764cb6475e83d86796789a4725095e317efd3c62ce3 +size 16068891200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0f8350a --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: circulus/Llama-3-Lunar-8B-v0.1 +language: +- en +library_name: transformers +license: gpl-3.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/circulus/Llama-3-Lunar-8B-v0.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-Lunar-8B-v0.1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-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/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Lunar-8B-v0.1-GGUF/resolve/main/Llama-3-Lunar-8B-v0.1.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. + +