commit f5ece491459f67425ce37715b7216db446093558 Author: ModelHub XC Date: Sun Oct 11 05:25:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..94b8dc4 --- /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 +NanoLlama-GQA-L10-A32_KV8-v13-KI.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NanoLlama-GQA-L10-A32_KV8-v13-KI.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.IQ4_XS.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.IQ4_XS.gguf new file mode 100644 index 0000000..ffd8730 --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4840a47d9817dbe87145604fa0bf0c77ef244b9332bd086a9b9baba7fc598916 +size 127123072 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q2_K.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q2_K.gguf new file mode 100644 index 0000000..92c9feb --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee5745af38d9e45b04bed067e5e83241d5a90d8ca122f7d1cdc9299406b86744 +size 94430848 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_L.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_L.gguf new file mode 100644 index 0000000..19081d5 --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92255455d250b453dc8cff2c37468c692d7428aa062404791725da4c1d20187f +size 121467520 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_M.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_M.gguf new file mode 100644 index 0000000..94c65bf --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bd1a4c7265999eeb0ef5d23f82b095b9439fd244cb1dc8966776fdfeef0bf0f +size 114651776 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_S.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_S.gguf new file mode 100644 index 0000000..e015297 --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d698900c92c57690816ffc7f0f47228424bd635181185ab6d31832ba2f0c41 +size 107274880 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_M.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_M.gguf new file mode 100644 index 0000000..ec11477 --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f53bdcb11e70b7f389001d31388a01e7f6b909ff43775a5ab92913b1f609428e +size 137582208 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_S.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_S.gguf new file mode 100644 index 0000000..dddcc82 --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82428acb33e8e717c68f06fd7e6413ab416286b5791ee0054e4fc54de3e7fe6a +size 132492928 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_M.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_M.gguf new file mode 100644 index 0000000..1b3c963 --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e7ffa07bc202ffaefbe9d7c2657651fea1943691d2d007a7d7180a524bc8ea +size 157914752 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_S.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_S.gguf new file mode 100644 index 0000000..abaeedb --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58794bae53aaf1e916b9e7c7c2ee88e22d8d69e139d5fe22e3bdffb2f42d77f1 +size 154955392 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q6_K.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q6_K.gguf new file mode 100644 index 0000000..958142d --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:800521ed0cc51aae218d23effbdce5d5881e2c08a46f26efcb8336dccdf3ec83 +size 179518080 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q8_0.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q8_0.gguf new file mode 100644 index 0000000..f320c32 --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b9d4072012cd03b0e98fd38937782a96416ecdc02142263cb0d7583900ac124 +size 232276608 diff --git a/NanoLlama-GQA-L10-A32_KV8-v13-KI.f16.gguf b/NanoLlama-GQA-L10-A32_KV8-v13-KI.f16.gguf new file mode 100644 index 0000000..67e4edf --- /dev/null +++ b/NanoLlama-GQA-L10-A32_KV8-v13-KI.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0bfcccc9523bb2e2ec3bc5f93446643c68d897cd8003cf1c87334dd4b2bcd97 +size 436503168 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a59331 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: BEE-spoke-data/NanoLlama-GQA-L10-A32_KV8-v13-KI +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- smol_llama +- llama2 +--- +## About + + + + + + +static quants of https://huggingface.co/BEE-spoke-data/NanoLlama-GQA-L10-A32_KV8-v13-KI + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NanoLlama-GQA-L10-A32_KV8-v13-KI-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/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_S.gguf) | Q5_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q5_K_M.gguf) | Q5_K_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q6_K.gguf) | Q6_K | 0.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NanoLlama-GQA-L10-A32_KV8-v13-KI-GGUF/resolve/main/NanoLlama-GQA-L10-A32_KV8-v13-KI.f16.gguf) | f16 | 0.5 | 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. + +