commit 9b67c4e2b220f093eb66c1f59bfbce8fd536b7aa Author: ModelHub XC Date: Thu Jul 9 21:42:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b3e9809 --- /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 +Llama-3.2-1B-MATH-GRPO-LEAD.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-MATH-GRPO-LEAD.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.IQ4_XS.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.IQ4_XS.gguf new file mode 100644 index 0000000..8ce5b0d --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b0af306ba5081b4ebf0f5284e14ad03dcc2086afa2064ebaf82f75d58b83ed +size 887927072 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q2_K.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q2_K.gguf new file mode 100644 index 0000000..d47ee20 --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3245c1bd24bd35c34e0d52db09a208845f4c4397189698b160f7a020e14514d +size 667062560 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_L.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_L.gguf new file mode 100644 index 0000000..918d043 --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:069a76f2f53ee9ad3494968fb1f6c2a6dc2b1223febccb1e8df4e1fd07cbf5f1 +size 845390112 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_M.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_M.gguf new file mode 100644 index 0000000..cce646e --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0391a95aa4da4937e4b3de39f1cb41cc34d43939459a7ddee93247e2d7f26227 +size 803709216 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_S.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_S.gguf new file mode 100644 index 0000000..b3b998d --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c674d36bd5a53f8b2485d1644e25e8d44ee1d95bfdbb0f7dd13a10f14546e141 +size 754557216 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_M.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_M.gguf new file mode 100644 index 0000000..eba163a --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560d2451c6ac31ab67542dc079bd4750cf24627c5912cb055ec86cf8242e95d5 +size 955445536 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_S.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_S.gguf new file mode 100644 index 0000000..80ce838 --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74bf2c4141860c30b531d5e365ff6d75f25188ecadee06c5126de5acb65ca138 +size 923398432 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_M.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_M.gguf new file mode 100644 index 0000000..10c5be9 --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b8ef8ba09d2d12e659415fdaa7dbc15912f7ee3a123528b7aab64094081c80 +size 1092088096 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_S.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_S.gguf new file mode 100644 index 0000000..1ead934 --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fb89dfd890be432dad00b407d90200b419c6def0829502f85b6162102114878 +size 1073148192 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q6_K.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q6_K.gguf new file mode 100644 index 0000000..959dd62 --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c6e73966b1934bcab3a35f1a728a3412601fab254ed9ac34f1e1cba1ea9845 +size 1237270816 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.Q8_0.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.Q8_0.gguf new file mode 100644 index 0000000..1685e57 --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0663ebdf3672173242630e13f4f23b1b0c433bdb0953ed8ca759f68f6a944528 +size 1600168224 diff --git a/Llama-3.2-1B-MATH-GRPO-LEAD.f16.gguf b/Llama-3.2-1B-MATH-GRPO-LEAD.f16.gguf new file mode 100644 index 0000000..eebd98d --- /dev/null +++ b/Llama-3.2-1B-MATH-GRPO-LEAD.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9649572d90326e00075fb4bf6e17038e7ef57b57e14c89eca7ad14149f8112a6 +size 3004932384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f97c8b3 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: lhkhiem28/Llama-3.2-1B-MATH-GRPO-LEAD +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/lhkhiem28/Llama-3.2-1B-MATH-GRPO-LEAD + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-MATH-GRPO-LEAD-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/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-MATH-GRPO-LEAD-GGUF/resolve/main/Llama-3.2-1B-MATH-GRPO-LEAD.f16.gguf) | f16 | 3.1 | 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. + +