commit 2965c96e8a427d9ac702d7df8477e89d61fa5e73 Author: ModelHub XC Date: Tue Apr 21 20:20:42 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Express.1-Tiny-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c3b1bf2 --- /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-Express.1-Tiny.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Tiny.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Express.1-Tiny.IQ4_XS.gguf b/Llama-Express.1-Tiny.IQ4_XS.gguf new file mode 100644 index 0000000..0bdf988 --- /dev/null +++ b/Llama-Express.1-Tiny.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4265ed76a62a883b463b1e0e957f40e2a37fe80c421e317265110ae3e7f7959 +size 748385600 diff --git a/Llama-Express.1-Tiny.Q2_K.gguf b/Llama-Express.1-Tiny.Q2_K.gguf new file mode 100644 index 0000000..e157751 --- /dev/null +++ b/Llama-Express.1-Tiny.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476496844dadcf83126765b931003d009365bc0cd0c4470c411a0719004486ca +size 580875584 diff --git a/Llama-Express.1-Tiny.Q3_K_L.gguf b/Llama-Express.1-Tiny.Q3_K_L.gguf new file mode 100644 index 0000000..9a1840d --- /dev/null +++ b/Llama-Express.1-Tiny.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21cbcdf68e2ca3e65b6bac4ce831b6cc9b22fc2b69d2bdd514354824b5436b9 +size 732525888 diff --git a/Llama-Express.1-Tiny.Q3_K_M.gguf b/Llama-Express.1-Tiny.Q3_K_M.gguf new file mode 100644 index 0000000..f3b5c17 --- /dev/null +++ b/Llama-Express.1-Tiny.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf61e0198c7d1aad3fd055c696e492c8175aca803c09a7375715742cf5f0157 +size 690844992 diff --git a/Llama-Express.1-Tiny.Q3_K_S.gguf b/Llama-Express.1-Tiny.Q3_K_S.gguf new file mode 100644 index 0000000..dcdfde0 --- /dev/null +++ b/Llama-Express.1-Tiny.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4002b80d07e6273ebda106221c3c28d933e6563571d23a4ff544ea49d3a5bb8 +size 641692992 diff --git a/Llama-Express.1-Tiny.Q4_K_M.gguf b/Llama-Express.1-Tiny.Q4_K_M.gguf new file mode 100644 index 0000000..01111a6 --- /dev/null +++ b/Llama-Express.1-Tiny.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52c017858beb790a3c0a09d9c09039edf3b5940258ea2817a90390188b16e2a3 +size 807695680 diff --git a/Llama-Express.1-Tiny.Q4_K_S.gguf b/Llama-Express.1-Tiny.Q4_K_S.gguf new file mode 100644 index 0000000..a95b8d4 --- /dev/null +++ b/Llama-Express.1-Tiny.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52c8bbdc1eb2af276c80d96c6f4301b3b436a5273c778e65fdef9a48414fc61 +size 775648576 diff --git a/Llama-Express.1-Tiny.Q5_K_M.gguf b/Llama-Express.1-Tiny.Q5_K_M.gguf new file mode 100644 index 0000000..ead892e --- /dev/null +++ b/Llama-Express.1-Tiny.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f16afbe378aa6d5e6a27c63f14ca262897c957a641a1f9c600496ea2a091f43 +size 911504704 diff --git a/Llama-Express.1-Tiny.Q5_K_S.gguf b/Llama-Express.1-Tiny.Q5_K_S.gguf new file mode 100644 index 0000000..3457fc7 --- /dev/null +++ b/Llama-Express.1-Tiny.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e6bc267ebef4a8730a48f2a05c6db2e537be544898412ad401e6cac95cbd0a +size 892564800 diff --git a/Llama-Express.1-Tiny.Q6_K.gguf b/Llama-Express.1-Tiny.Q6_K.gguf new file mode 100644 index 0000000..fe13dd3 --- /dev/null +++ b/Llama-Express.1-Tiny.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872e91bcc3688e02e5d07ea0ccb67ca413a6bedd796f662317df59cb1ab4763e +size 1021801792 diff --git a/Llama-Express.1-Tiny.Q8_0.gguf b/Llama-Express.1-Tiny.Q8_0.gguf new file mode 100644 index 0000000..3b9408d --- /dev/null +++ b/Llama-Express.1-Tiny.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:effb5257c77b74dcbd943b2e910c2f1c9b7e5e8b3ae5f5de8d21f1ae7508fc98 +size 1321084224 diff --git a/Llama-Express.1-Tiny.f16.gguf b/Llama-Express.1-Tiny.f16.gguf new file mode 100644 index 0000000..7083078 --- /dev/null +++ b/Llama-Express.1-Tiny.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc23841718ce451a575c6b6bb09cc446bb6000f65024ff4dda7d491be73ed31 +size 2479596864 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e79247 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: prithivMLmods/Llama-Express.1-Tiny +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- thinker +- llama +- express +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Llama-Express.1-Tiny + + +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-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Tiny-GGUF/resolve/main/Llama-Express.1-Tiny.f16.gguf) | f16 | 2.6 | 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. + +