commit 64712749f84d40cee339cdfbf95a7a8405d2d021 Author: ModelHub XC Date: Mon Oct 12 12:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/nanollama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cd71698 --- /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.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +nanollama.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5d99f5a --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: imdatta0/nanollama +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/imdatta0/nanollama + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#nanollama-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-GGUF/resolve/main/nanollama.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.Q5_K_S.gguf) | Q5_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.Q5_K_M.gguf) | Q5_K_M | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.Q6_K.gguf) | Q6_K | 0.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.Q8_0.gguf) | Q8_0 | 0.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/nanollama-GGUF/resolve/main/nanollama.f16.gguf) | f16 | 0.7 | 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/nanollama.IQ4_XS.gguf b/nanollama.IQ4_XS.gguf new file mode 100644 index 0000000..ef19a8a --- /dev/null +++ b/nanollama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a319929a885f5d501c77a36eb9fe9c94e5fff0646b1446a89b9cb747364db6 +size 194804448 diff --git a/nanollama.Q2_K.gguf b/nanollama.Q2_K.gguf new file mode 100644 index 0000000..800c7db --- /dev/null +++ b/nanollama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a6ceb1d9bc809e7d3c06a2b1aa2db15c1f13c2e5bc1cc4236b8a13d9b9f5e27 +size 163175136 diff --git a/nanollama.Q3_K_L.gguf b/nanollama.Q3_K_L.gguf new file mode 100644 index 0000000..ca15a7a --- /dev/null +++ b/nanollama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6810a7d68070884af4cfc100d516ea088f45c5a047a6794ec0e1f0d7ed52ca86 +size 181336800 diff --git a/nanollama.Q3_K_M.gguf b/nanollama.Q3_K_M.gguf new file mode 100644 index 0000000..87eb099 --- /dev/null +++ b/nanollama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8241edcbb870dc81987ba2116ca078ce44838890c013d638c0b2a219d95557d7 +size 180091616 diff --git a/nanollama.Q3_K_S.gguf b/nanollama.Q3_K_S.gguf new file mode 100644 index 0000000..7119ce0 --- /dev/null +++ b/nanollama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e7ae514030b8b688d7fe54a5945b0d9b9a16d39e198a4c9c408dcac3fa2173 +size 178510560 diff --git a/nanollama.Q4_K_M.gguf b/nanollama.Q4_K_M.gguf new file mode 100644 index 0000000..17c0adc --- /dev/null +++ b/nanollama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7020ec1094dd77ddf341082a4df19e5443c66566dbfe41db951d5ec7cfc37143 +size 201296608 diff --git a/nanollama.Q4_K_S.gguf b/nanollama.Q4_K_S.gguf new file mode 100644 index 0000000..2149d7e --- /dev/null +++ b/nanollama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b40c063a5e62cf65d276e17375377dcf0353675b96ae037a794f2389b80c3a82 +size 200211168 diff --git a/nanollama.Q5_K_M.gguf b/nanollama.Q5_K_M.gguf new file mode 100644 index 0000000..dbaf11d --- /dev/null +++ b/nanollama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e905ca1cde766b6c43df65e017b8001c335d67c004377f589813f6ef01f29789 +size 220891872 diff --git a/nanollama.Q5_K_S.gguf b/nanollama.Q5_K_S.gguf new file mode 100644 index 0000000..66852bd --- /dev/null +++ b/nanollama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d36cea1fefa0d86b5c83e3c0d753830bff1a83294c38d0a346276fc67517417a +size 220265184 diff --git a/nanollama.Q6_K.gguf b/nanollama.Q6_K.gguf new file mode 100644 index 0000000..b01ef1b --- /dev/null +++ b/nanollama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b1a0db4500bebafd56d368da0074d15f79508276390d4c8f9b85b3551f66fd +size 242227936 diff --git a/nanollama.Q8_0.gguf b/nanollama.Q8_0.gguf new file mode 100644 index 0000000..b7580ba --- /dev/null +++ b/nanollama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca61cd5abd30495574aa7ebecb39020302a0353d3d1122822e9c4fbf6688365 +size 312826592 diff --git a/nanollama.f16.gguf b/nanollama.f16.gguf new file mode 100644 index 0000000..d2d6ce8 --- /dev/null +++ b/nanollama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9a08058fd162990348a155ba532c47157777377ee4b45255ec554e12b74a4f +size 588077792