commit 00c53d40a9662678d50026498dd6a19177af7e67 Author: ModelHub XC Date: Tue Jun 2 16:31:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NanoLM-1B-Instruct-v1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3a2e480 --- /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 +NanoLM-1B-Instruct-v1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NanoLM-1B-Instruct-v1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NanoLM-1B-Instruct-v1.1.IQ4_XS.gguf b/NanoLM-1B-Instruct-v1.1.IQ4_XS.gguf new file mode 100644 index 0000000..9a1eabb --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c6cae2793edc2bba16d860bf7583c7f76f3e655674a35111de64841df7281b +size 650618496 diff --git a/NanoLM-1B-Instruct-v1.1.Q2_K.gguf b/NanoLM-1B-Instruct-v1.1.Q2_K.gguf new file mode 100644 index 0000000..575968f --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf6bb48618a96cf467fa9d1eafd248e1b3aea8b96343ce533e01bfcc495b2a3 +size 505257600 diff --git a/NanoLM-1B-Instruct-v1.1.Q3_K_L.gguf b/NanoLM-1B-Instruct-v1.1.Q3_K_L.gguf new file mode 100644 index 0000000..143bc15 --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:233fd126d0cbfee0b9d04a95f98f63a5886540d24c818765ec09922e57072616 +size 636309120 diff --git a/NanoLM-1B-Instruct-v1.1.Q3_K_M.gguf b/NanoLM-1B-Instruct-v1.1.Q3_K_M.gguf new file mode 100644 index 0000000..2758510 --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9194fa7e354e6b79b9ea4491bcaa1a2b534da6ea8c75e43e645ebde8ab9e0ef +size 600968832 diff --git a/NanoLM-1B-Instruct-v1.1.Q3_K_S.gguf b/NanoLM-1B-Instruct-v1.1.Q3_K_S.gguf new file mode 100644 index 0000000..e9302c2 --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a649041c75f1629cbf0880f1f9b55bf16c36bb070f5118c519a5c7e05c5d70 +size 559668864 diff --git a/NanoLM-1B-Instruct-v1.1.Q4_K_M.gguf b/NanoLM-1B-Instruct-v1.1.Q4_K_M.gguf new file mode 100644 index 0000000..d0ff2b8 --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93cef2c5e7afea541ad259218298de56ad6e0cc113113be2723458064da5762a +size 704378496 diff --git a/NanoLM-1B-Instruct-v1.1.Q4_K_S.gguf b/NanoLM-1B-Instruct-v1.1.Q4_K_S.gguf new file mode 100644 index 0000000..4fb3d2f --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5c793d51e0de6db39ff237ef85c9e4ad3de3b28c43a05b515ef51b4fcd3efe7 +size 675169920 diff --git a/NanoLM-1B-Instruct-v1.1.Q5_K_M.gguf b/NanoLM-1B-Instruct-v1.1.Q5_K_M.gguf new file mode 100644 index 0000000..4371529 --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff89a0d0cab1886b97f3b5ecf3ddc815a7e8391591b77bc65998f5e603aeb848 +size 793736832 diff --git a/NanoLM-1B-Instruct-v1.1.Q5_K_S.gguf b/NanoLM-1B-Instruct-v1.1.Q5_K_S.gguf new file mode 100644 index 0000000..3cc9364 --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389e5d6d9cb4fc067e6f62a4c47b47570b316f98e464b479c0d5be66f589d5cb +size 776816256 diff --git a/NanoLM-1B-Instruct-v1.1.Q6_K.gguf b/NanoLM-1B-Instruct-v1.1.Q6_K.gguf new file mode 100644 index 0000000..8ef7a53 --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:002346751ef15163d495e997f67caf2e991a98112fb3108bb78e22122eff7f97 +size 888680064 diff --git a/NanoLM-1B-Instruct-v1.1.Q8_0.gguf b/NanoLM-1B-Instruct-v1.1.Q8_0.gguf new file mode 100644 index 0000000..c6b7254 --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61753d9fae827dbadc428246038758f30e2123aa1dbd88f923cbeef1f874812 +size 1149187200 diff --git a/NanoLM-1B-Instruct-v1.1.f16.gguf b/NanoLM-1B-Instruct-v1.1.f16.gguf new file mode 100644 index 0000000..31ed219 --- /dev/null +++ b/NanoLM-1B-Instruct-v1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce0d0cfb2cdca95328734ae646255dc1681856235c5c0fb15aef3f86dd5bf5a +size 2157601920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ea75c09 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: Mxode/NanoLM-1B-Instruct-v1.1 +datasets: +- Mxode/Magpie-Pro-10K-GPT4o-mini +language: +- en +library_name: transformers +license: gpl-3.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- chemistry +- biology +- finance +- legal +- music +- art +- code +- climate +- medical +- text-generation-inference +--- +## About + + + + + + +static quants of https://huggingface.co/Mxode/NanoLM-1B-Instruct-v1.1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#NanoLM-1B-Instruct-v1.1-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/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q2_K.gguf) | Q2_K | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.Q8_0.gguf) | Q8_0 | 1.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NanoLM-1B-Instruct-v1.1-GGUF/resolve/main/NanoLM-1B-Instruct-v1.1.f16.gguf) | f16 | 2.3 | 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. + +