commit e0cd1c059d4399020d59b3f22104276a55e6a83e Author: ModelHub XC Date: Thu Jun 4 01:56:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NosirAI-Mini-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9cca696 --- /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 +NosirAI-Mini.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NosirAI-Mini.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NosirAI-Mini.IQ4_XS.gguf b/NosirAI-Mini.IQ4_XS.gguf new file mode 100644 index 0000000..8385347 --- /dev/null +++ b/NosirAI-Mini.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3374bf71d196066474859a034ccfa5c73aed8cdd93db5b581ed389a81428b27 +size 1840907264 diff --git a/NosirAI-Mini.Q2_K.gguf b/NosirAI-Mini.Q2_K.gguf new file mode 100644 index 0000000..1e25ff6 --- /dev/null +++ b/NosirAI-Mini.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1a6ac97e5deaf7fb1f98924f057496bd50085d3f65a91a8c770148c0ddbb83 +size 1363936256 diff --git a/NosirAI-Mini.Q3_K_L.gguf b/NosirAI-Mini.Q3_K_L.gguf new file mode 100644 index 0000000..191c1fc --- /dev/null +++ b/NosirAI-Mini.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10e9d78c93e0d3b3f344443bdca3516cb169d6ec0e06b07de6be244b0945122b +size 1815348224 diff --git a/NosirAI-Mini.Q3_K_M.gguf b/NosirAI-Mini.Q3_K_M.gguf new file mode 100644 index 0000000..ccd9dba --- /dev/null +++ b/NosirAI-Mini.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb952c70780eb029ada2c36499d075f81c5ac48a8b7aa5e6e8b558fa52d50a4 +size 1687159808 diff --git a/NosirAI-Mini.Q3_K_S.gguf b/NosirAI-Mini.Q3_K_S.gguf new file mode 100644 index 0000000..45b30cc --- /dev/null +++ b/NosirAI-Mini.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ef1f4e79d3b451944880d0ea20998b4d10fba69b180f8387c459cc90a9a2295 +size 1542849536 diff --git a/NosirAI-Mini.Q4_K_M.gguf b/NosirAI-Mini.Q4_K_M.gguf new file mode 100644 index 0000000..31623b1 --- /dev/null +++ b/NosirAI-Mini.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b3d801a4f16fd9dc4f2d1a31164e924abc49d3921842a3a8f895af5ef5c63a9 +size 2019378176 diff --git a/NosirAI-Mini.Q4_K_S.gguf b/NosirAI-Mini.Q4_K_S.gguf new file mode 100644 index 0000000..e1233c2 --- /dev/null +++ b/NosirAI-Mini.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1b09d6f66a5e9226a41a619bf61cf62c5ff275d1bb58c75023e90cce022b5f +size 1928201216 diff --git a/NosirAI-Mini.Q5_K_M.gguf b/NosirAI-Mini.Q5_K_M.gguf new file mode 100644 index 0000000..b262ba2 --- /dev/null +++ b/NosirAI-Mini.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab5d9fa34fd1e56b8b92b5cbec985fe722f238581c7101f4bfaa426592d3ee2 +size 2322154496 diff --git a/NosirAI-Mini.Q5_K_S.gguf b/NosirAI-Mini.Q5_K_S.gguf new file mode 100644 index 0000000..6d9d94f --- /dev/null +++ b/NosirAI-Mini.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a10ebd3a8cc035471648b143cca6fd227f4b61f6e70f3ef334b3451a8a20023 +size 2269512704 diff --git a/NosirAI-Mini.Q6_K.gguf b/NosirAI-Mini.Q6_K.gguf new file mode 100644 index 0000000..b792f4f --- /dev/null +++ b/NosirAI-Mini.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2ea01d652a957de9ce07910d1d7cea5765599cfd30882cec21e97ce630ac009 +size 2643854336 diff --git a/NosirAI-Mini.Q8_0.gguf b/NosirAI-Mini.Q8_0.gguf new file mode 100644 index 0000000..bf4fb0b --- /dev/null +++ b/NosirAI-Mini.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e46e56ccdfde8c022cf478f73c85b1dba1843729df527cc8ed2012cd77fb5f +size 3421899776 diff --git a/NosirAI-Mini.f16.gguf b/NosirAI-Mini.f16.gguf new file mode 100644 index 0000000..090cf80 --- /dev/null +++ b/NosirAI-Mini.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:053e16c2b0712423c6b86c9ae21591c80ef53ad29c3ba6b6ac9c7907025c47c4 +size 6433688576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..41c6a25 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: hamdanbinhashim/NosirAI-Mini +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hamdanbinhashim/NosirAI-Mini + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NosirAI-Mini-GGUF).*** + +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/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NosirAI-Mini-GGUF/resolve/main/NosirAI-Mini.f16.gguf) | f16 | 6.5 | 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. + +