commit 5fdb9b0ac9ccdaac71fd1c10280e791db887710d Author: ModelHub XC Date: Wed May 20 23:40:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-DMS-8x-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..86eab5a --- /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-3.2-1B-DMS-8x.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-DMS-8x.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-DMS-8x.IQ4_XS.gguf b/Llama-3.2-1B-DMS-8x.IQ4_XS.gguf new file mode 100644 index 0000000..d3b5f52 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c6ef92ce598dd8fa37fb8eed5258ce50e81e58cdefef713f66b80cbd797dff +size 748381312 diff --git a/Llama-3.2-1B-DMS-8x.Q2_K.gguf b/Llama-3.2-1B-DMS-8x.Q2_K.gguf new file mode 100644 index 0000000..62a0110 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b8cb45225a0a8e643ec8bbea584ba428922dc436a7b2a3f9c1180096ca0548 +size 580871296 diff --git a/Llama-3.2-1B-DMS-8x.Q3_K_L.gguf b/Llama-3.2-1B-DMS-8x.Q3_K_L.gguf new file mode 100644 index 0000000..780bff0 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:684aab0a59043288274378f546733c7163d140ab0cdf09c1e4ab4974d7c75aa6 +size 732521600 diff --git a/Llama-3.2-1B-DMS-8x.Q3_K_M.gguf b/Llama-3.2-1B-DMS-8x.Q3_K_M.gguf new file mode 100644 index 0000000..e722cad --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d97a2a9be061d192d4345f758087a64556a28c67f2df8f64482577bf8c19e573 +size 690840704 diff --git a/Llama-3.2-1B-DMS-8x.Q3_K_S.gguf b/Llama-3.2-1B-DMS-8x.Q3_K_S.gguf new file mode 100644 index 0000000..45700a7 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205d852a0c09f2e964152c700d3ff71f0538cac8aae285113800ebf858ca9bb7 +size 641688704 diff --git a/Llama-3.2-1B-DMS-8x.Q4_K_M.gguf b/Llama-3.2-1B-DMS-8x.Q4_K_M.gguf new file mode 100644 index 0000000..b7ac240 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e92272ba8d23116c825bb6ba853715ee386d3ab119b06d53bfdb5219cafec44 +size 807691392 diff --git a/Llama-3.2-1B-DMS-8x.Q4_K_S.gguf b/Llama-3.2-1B-DMS-8x.Q4_K_S.gguf new file mode 100644 index 0000000..148f7e5 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87200f2197e0aaf84e3fff45e19fa8ef5d5ab6574ff01e22d6c0d115d962062f +size 775644288 diff --git a/Llama-3.2-1B-DMS-8x.Q5_K_M.gguf b/Llama-3.2-1B-DMS-8x.Q5_K_M.gguf new file mode 100644 index 0000000..cd266cd --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28887fe9a6db145d1d674c014e44c77362a7395968b73cb5fcb2a1438684e055 +size 911500416 diff --git a/Llama-3.2-1B-DMS-8x.Q5_K_S.gguf b/Llama-3.2-1B-DMS-8x.Q5_K_S.gguf new file mode 100644 index 0000000..42ada74 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f598d183fc4dbf2d63fce00134392da48121994a201f1662e6fdc7bf74490a +size 892560512 diff --git a/Llama-3.2-1B-DMS-8x.Q6_K.gguf b/Llama-3.2-1B-DMS-8x.Q6_K.gguf new file mode 100644 index 0000000..d018fa0 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f361311da7345247d7065324112c3f235c105ed3a196056e79ca79dcfd2c1f6 +size 1021797504 diff --git a/Llama-3.2-1B-DMS-8x.Q8_0.gguf b/Llama-3.2-1B-DMS-8x.Q8_0.gguf new file mode 100644 index 0000000..0108321 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9e2125e233039e10b40f684c1e4cc253fca575bf3cdc198218d55bc8ed16216 +size 1321079936 diff --git a/Llama-3.2-1B-DMS-8x.f16.gguf b/Llama-3.2-1B-DMS-8x.f16.gguf new file mode 100644 index 0000000..c488272 --- /dev/null +++ b/Llama-3.2-1B-DMS-8x.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcedcadb359243cc3fe0a21e0228ab7b3e7dc820b963edbcc46b8abb92f9938e +size 2479592576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..33898bf --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: shisa-ai/Llama-3.2-1B-DMS-8x +datasets: +- Salesforce/wikitext +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- shisa-ai +- llama +- llama-3.2 +- pytorch +- kvcache +- dms +- fastdms +- kv-cache-compression +--- +## About + + + + + + + + + +static quants of https://huggingface.co/shisa-ai/Llama-3.2-1B-DMS-8x + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-DMS-8x-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-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-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-DMS-8x-GGUF/resolve/main/Llama-3.2-1B-DMS-8x.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. + +