commit a8e7d2cdfba2e655f1a4edd79f9e20753536d9d4 Author: ModelHub XC Date: Mon May 11 18:03:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-5.4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..919b5dc --- /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-3.1-5.4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-5.4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-5.4B.IQ4_XS.gguf b/Llama-3.1-5.4B.IQ4_XS.gguf new file mode 100644 index 0000000..f43300f --- /dev/null +++ b/Llama-3.1-5.4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec64863fd164f3609a90e7c17d643777c5ac5fbadf874844f9f020291a1bfde +size 3067337376 diff --git a/Llama-3.1-5.4B.Q2_K.gguf b/Llama-3.1-5.4B.Q2_K.gguf new file mode 100644 index 0000000..2b612f4 --- /dev/null +++ b/Llama-3.1-5.4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa282ebdeb986ce0a451527c3e5a65dec1dad4a85e6ce532894ca15982eec25 +size 2216139424 diff --git a/Llama-3.1-5.4B.Q3_K_L.gguf b/Llama-3.1-5.4B.Q3_K_L.gguf new file mode 100644 index 0000000..3814650 --- /dev/null +++ b/Llama-3.1-5.4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56927486c9a0cd08d9a5bac4ce8776a4e7ea825e00238275073ae5e4381967cb +size 2950412960 diff --git a/Llama-3.1-5.4B.Q3_K_M.gguf b/Llama-3.1-5.4B.Q3_K_M.gguf new file mode 100644 index 0000000..9439666 --- /dev/null +++ b/Llama-3.1-5.4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9648b014f4354fcc2ddfe569c3a4f3525e61c1de7e7352a2677753750e1f27 +size 2759572128 diff --git a/Llama-3.1-5.4B.Q3_K_S.gguf b/Llama-3.1-5.4B.Q3_K_S.gguf new file mode 100644 index 0000000..17b4232 --- /dev/null +++ b/Llama-3.1-5.4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b390618f315c09b7328fb7fc3e8d0060b4d9ccfb68df55b7adf1ea355c220f48 +size 2539502240 diff --git a/Llama-3.1-5.4B.Q4_K_M.gguf b/Llama-3.1-5.4B.Q4_K_M.gguf new file mode 100644 index 0000000..dac8a8e --- /dev/null +++ b/Llama-3.1-5.4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b17776a39ab0d4c737e31e6ae5538790c3f66ffa656a52ea73e6fa1748dd749 +size 3350813344 diff --git a/Llama-3.1-5.4B.Q4_K_S.gguf b/Llama-3.1-5.4B.Q4_K_S.gguf new file mode 100644 index 0000000..b35f935 --- /dev/null +++ b/Llama-3.1-5.4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c144cdf7107e8bb9c2d451f666cf0300c9604c7e0ef68be9555800a8339ec57 +size 3205388960 diff --git a/Llama-3.1-5.4B.Q5_K_M.gguf b/Llama-3.1-5.4B.Q5_K_M.gguf new file mode 100644 index 0000000..a1562eb --- /dev/null +++ b/Llama-3.1-5.4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91827dd74c8ac11028b2b35239cfee0c5282620bd3a0ad94bf3486f81aa5d5df +size 3883096736 diff --git a/Llama-3.1-5.4B.Q5_K_S.gguf b/Llama-3.1-5.4B.Q5_K_S.gguf new file mode 100644 index 0000000..42fbf1b --- /dev/null +++ b/Llama-3.1-5.4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96c70f2814c2406e2395a6a081ed55d7c4b78a39f0cbeb7959a39e8bb094a1a7 +size 3799538336 diff --git a/Llama-3.1-5.4B.Q6_K.gguf b/Llama-3.1-5.4B.Q6_K.gguf new file mode 100644 index 0000000..0c3a484 --- /dev/null +++ b/Llama-3.1-5.4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18db169c139362aa426488bb000eb233aa5d5ef6ef451b58dc164c0f189a60f5 +size 4448647840 diff --git a/Llama-3.1-5.4B.Q8_0.gguf b/Llama-3.1-5.4B.Q8_0.gguf new file mode 100644 index 0000000..51e7ff1 --- /dev/null +++ b/Llama-3.1-5.4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24a33ffb37a65ddab2f760efe694c6816a9ce1d0f1d03dbc95066fe508d8450 +size 5759548064 diff --git a/Llama-3.1-5.4B.f16.gguf b/Llama-3.1-5.4B.f16.gguf new file mode 100644 index 0000000..0384ed7 --- /dev/null +++ b/Llama-3.1-5.4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b513a709c018cb86ba87c7522848d0e6aff16a6da9c88a10dc0806b5cf7e07 +size 10834000544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..215f460 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: XiaodongChen/Llama-3.1-5.4B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/XiaodongChen/Llama-3.1-5.4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.1-5.4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-5.4B-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-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q2_K.gguf) | Q2_K | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q3_K_S.gguf) | Q3_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q3_K_M.gguf) | Q3_K_M | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q3_K_L.gguf) | Q3_K_L | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.IQ4_XS.gguf) | IQ4_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q4_K_S.gguf) | Q4_K_S | 3.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q4_K_M.gguf) | Q4_K_M | 3.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q5_K_S.gguf) | Q5_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q5_K_M.gguf) | Q5_K_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q6_K.gguf) | Q6_K | 4.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.Q8_0.gguf) | Q8_0 | 5.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-5.4B-GGUF/resolve/main/Llama-3.1-5.4B.f16.gguf) | f16 | 10.9 | 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. + +