commit dcdc2a33f9f62eba80a8f2f0488b05504425f619 Author: ModelHub XC Date: Wed Sep 23 23:31:18 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..03455db --- /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 +Wide-Sheared-LLaMA-1.3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Wide-Sheared-LLaMA-1.3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..63146bd --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: minghaoyan/Wide-Sheared-LLaMA-1.3B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/minghaoyan/Wide-Sheared-LLaMA-1.3B + + +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/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q5_K_M.gguf) | Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.Q8_0.gguf) | Q8_0 | 1.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Wide-Sheared-LLaMA-1.3B-GGUF/resolve/main/Wide-Sheared-LLaMA-1.3B.f16.gguf) | f16 | 2.8 | 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. + + diff --git a/Wide-Sheared-LLaMA-1.3B.IQ4_XS.gguf b/Wide-Sheared-LLaMA-1.3B.IQ4_XS.gguf new file mode 100644 index 0000000..49d08e5 --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c78248cd7acb4e9fdd7e22981f61d0f0e756a34d7766c8a4a5d1041f9b5d38 +size 746535904 diff --git a/Wide-Sheared-LLaMA-1.3B.Q2_K.gguf b/Wide-Sheared-LLaMA-1.3B.Q2_K.gguf new file mode 100644 index 0000000..3bbdbd8 --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b67aedd6968238dc43382d98509cae398ed53f43936eb4e8cb17b25f93107bed +size 561703904 diff --git a/Wide-Sheared-LLaMA-1.3B.Q3_K_L.gguf b/Wide-Sheared-LLaMA-1.3B.Q3_K_L.gguf new file mode 100644 index 0000000..1fb6cdc --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8572c203ce6f0d1e26a94bf6db6f92c1c445af9e667d40339a88adcfe61ba2f +size 737908704 diff --git a/Wide-Sheared-LLaMA-1.3B.Q3_K_M.gguf b/Wide-Sheared-LLaMA-1.3B.Q3_K_M.gguf new file mode 100644 index 0000000..6709f54 --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f30f0efc1680797597ff5715dad4dd360c96ec2a9c66563b16e21237d719ebb4 +size 702068704 diff --git a/Wide-Sheared-LLaMA-1.3B.Q3_K_S.gguf b/Wide-Sheared-LLaMA-1.3B.Q3_K_S.gguf new file mode 100644 index 0000000..8140a12 --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9e50db976d56001ad7e776029f4fed62cb6b100c44bdb9a415d17474890262 +size 643905504 diff --git a/Wide-Sheared-LLaMA-1.3B.Q4_K_M.gguf b/Wide-Sheared-LLaMA-1.3B.Q4_K_M.gguf new file mode 100644 index 0000000..55fd94e --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b0ba9be58410bbacf50a0b78a51ffe63c49b44cb2c3630fbba71ebcf21c1d9 +size 871515104 diff --git a/Wide-Sheared-LLaMA-1.3B.Q4_K_S.gguf b/Wide-Sheared-LLaMA-1.3B.Q4_K_S.gguf new file mode 100644 index 0000000..9da87e3 --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c4053d4001fc3e1d062e00685f6b6da3d3375b271f81d3b2e3cfc955255e2f +size 812686304 diff --git a/Wide-Sheared-LLaMA-1.3B.Q5_K_M.gguf b/Wide-Sheared-LLaMA-1.3B.Q5_K_M.gguf new file mode 100644 index 0000000..b1a3720 --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd41524448bcd2a0e6b8b96742cf1309d22b8c91e6bd20df3d29bb75d956caa +size 996340704 diff --git a/Wide-Sheared-LLaMA-1.3B.Q5_K_S.gguf b/Wide-Sheared-LLaMA-1.3B.Q5_K_S.gguf new file mode 100644 index 0000000..f8a1c02 --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffe551f9a6222e4f084c5115dab68117acbe755c7b476081038e655e5c65f1ab +size 946574304 diff --git a/Wide-Sheared-LLaMA-1.3B.Q6_K.gguf b/Wide-Sheared-LLaMA-1.3B.Q6_K.gguf new file mode 100644 index 0000000..69357f6 --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dd80c03344901297f63295079742280e5823b8b415a0c786a8469429def35b1 +size 1164046304 diff --git a/Wide-Sheared-LLaMA-1.3B.Q8_0.gguf b/Wide-Sheared-LLaMA-1.3B.Q8_0.gguf new file mode 100644 index 0000000..1cfa946 --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fd4eb9a6162f91710033c7707a6c892c21bcd03f5ce17845bf75e0ef6028c0 +size 1417998304 diff --git a/Wide-Sheared-LLaMA-1.3B.f16.gguf b/Wide-Sheared-LLaMA-1.3B.f16.gguf new file mode 100644 index 0000000..48f106e --- /dev/null +++ b/Wide-Sheared-LLaMA-1.3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d58a4273b1221874b7f9f34b45094804991b39ef3e71668503b799fb783a05 +size 2668302304