commit b9fbd475bade5cb40b3bb4d758ae76e055eb8b80 Author: ModelHub XC Date: Mon May 25 00:06:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PyNanoLM-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eb24793 --- /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 +PyNanoLM-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PyNanoLM-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PyNanoLM-v0.1.IQ4_XS.gguf b/PyNanoLM-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..0af4239 --- /dev/null +++ b/PyNanoLM-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6aa958f101c667104f4e50dab85786e7537267acc8a75188488c885e35024e +size 91313984 diff --git a/PyNanoLM-v0.1.Q2_K.gguf b/PyNanoLM-v0.1.Q2_K.gguf new file mode 100644 index 0000000..6b5e5ca --- /dev/null +++ b/PyNanoLM-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01bf7c4dd914de2856106705783a89880c7f5b667ee25bcaae8ed869bda6018d +size 88203584 diff --git a/PyNanoLM-v0.1.Q3_K_L.gguf b/PyNanoLM-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..0527289 --- /dev/null +++ b/PyNanoLM-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0de44287864ac0359c951298e0c3baabbf757e34f961473e51ccad2e9556c949 +size 97534784 diff --git a/PyNanoLM-v0.1.Q3_K_M.gguf b/PyNanoLM-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..d0cadba --- /dev/null +++ b/PyNanoLM-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ecfeb7fa7cd8151e18c2454dff994aece63ab5c7dc3547f239330547182967f +size 93512000 diff --git a/PyNanoLM-v0.1.Q3_K_S.gguf b/PyNanoLM-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..bd25ab0 --- /dev/null +++ b/PyNanoLM-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f1a23af7e91524576368bf9c08f39c33d64332552a644a272d3442f9b933f2 +size 88203584 diff --git a/PyNanoLM-v0.1.Q4_K_M.gguf b/PyNanoLM-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..b1f2ba5 --- /dev/null +++ b/PyNanoLM-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa57f62cffa956cc7f3b95bed218350f085216f8227beb1b90da1c68e8f3748 +size 105455936 diff --git a/PyNanoLM-v0.1.Q4_K_S.gguf b/PyNanoLM-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..5ccd416 --- /dev/null +++ b/PyNanoLM-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dfff3edc9c148c04086d589bb449f9ec1e48b829bcf02da76189598486fb5ed +size 102041408 diff --git a/PyNanoLM-v0.1.Q5_K_M.gguf b/PyNanoLM-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..8f5b987 --- /dev/null +++ b/PyNanoLM-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:694683d78016f06ff8cae859c8eaec5b930e2b947d10e0960a03f451fa30eda7 +size 112105280 diff --git a/PyNanoLM-v0.1.Q5_K_S.gguf b/PyNanoLM-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..e84a382 --- /dev/null +++ b/PyNanoLM-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29efdeeb8780b8674024c509ff618f4dbe4c4742c483f1bd33c0ebbf17d627c2 +size 109976384 diff --git a/PyNanoLM-v0.1.Q6_K.gguf b/PyNanoLM-v0.1.Q6_K.gguf new file mode 100644 index 0000000..4b33c97 --- /dev/null +++ b/PyNanoLM-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:400903b2bf3d5d50268400bcf7146bd5507c8c5c8e427b0d6a55abc19dc14c9d +size 138384704 diff --git a/PyNanoLM-v0.1.Q8_0.gguf b/PyNanoLM-v0.1.Q8_0.gguf new file mode 100644 index 0000000..1fa3088 --- /dev/null +++ b/PyNanoLM-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5310d4142721fa3256a9e11e2d03ea914c1acc77b55504c660ca26c15de50b4a +size 144812864 diff --git a/PyNanoLM-v0.1.f16.gguf b/PyNanoLM-v0.1.f16.gguf new file mode 100644 index 0000000..561762b --- /dev/null +++ b/PyNanoLM-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378c538c34e30fa426932a254787644ff3782992b8920e6bed9e873e603f7aca +size 270887744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0a6e60c --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: ShubhamSinghCodes/PyNanoLM-big +datasets: +- AI-MO/NuminaMath-CoT +- TIGER-Lab/MathInstruct +- Vezora/Tested-143k-Python-Alpaca +- glaiveai/glaive-code-assistant-v2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +- python +--- +## About + + + + + + +static quants of https://huggingface.co/ShubhamSinghCodes/PyNanoLM-big + + +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/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PyNanoLM-v0.1-GGUF/resolve/main/PyNanoLM-v0.1.f16.gguf) | f16 | 0.4 | 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. + +