commit 10f71135f46ccf9003b79323c8dc8863ca2d5fdc Author: ModelHub XC Date: Fri Sep 11 05:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..075c8e1 --- /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 +LLama3.2-3B-GSM8K-R1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.2-3B-GSM8K-R1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLama3.2-3B-GSM8K-R1.1.IQ4_XS.gguf b/LLama3.2-3B-GSM8K-R1.1.IQ4_XS.gguf new file mode 100644 index 0000000..f4bd473 --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba6a7921fb0da3f9eb7d8aa77ba2d0ce15364f5893c4810edf09b31e0830b151 +size 1840906880 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q2_K.gguf b/LLama3.2-3B-GSM8K-R1.1.Q2_K.gguf new file mode 100644 index 0000000..549addc --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7fb1b19c0bd36e8bec1e1fb28df1d39aebd8e4ee9241f01b42378e091f9bff1 +size 1363935872 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q3_K_L.gguf b/LLama3.2-3B-GSM8K-R1.1.Q3_K_L.gguf new file mode 100644 index 0000000..328e8c1 --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca750775e0cd7fcdd8c9a5a8a335f1fff98b3bb66ef53d33f3c3458c2a81e8f +size 1815347840 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q3_K_M.gguf b/LLama3.2-3B-GSM8K-R1.1.Q3_K_M.gguf new file mode 100644 index 0000000..974a9a0 --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e769c1835187723020aee6be21f165360051b3adddf83207fa16a3224ea1e16a +size 1687159424 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q3_K_S.gguf b/LLama3.2-3B-GSM8K-R1.1.Q3_K_S.gguf new file mode 100644 index 0000000..98de129 --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9386467f5dc4a0f9c6827307d1e73e7d115fc0e9c99beea9a23aad768cb728f +size 1542849152 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q4_K_M.gguf b/LLama3.2-3B-GSM8K-R1.1.Q4_K_M.gguf new file mode 100644 index 0000000..628a22c --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a855d623e89d2b8d8bb0e542046059836e3b2002454ee7d7f87233e8cfeeaa33 +size 2019377792 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q4_K_S.gguf b/LLama3.2-3B-GSM8K-R1.1.Q4_K_S.gguf new file mode 100644 index 0000000..604c077 --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0aa85a036a47b86ee1b36c5e60eb276d288d0bb047d68c5287572bb6f7aad55 +size 1928200832 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q5_K_M.gguf b/LLama3.2-3B-GSM8K-R1.1.Q5_K_M.gguf new file mode 100644 index 0000000..dc5a166 --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5a1817d6a534d259cdd029b8bc2f4ee9867c5968d639dd82db34ca896f98ca +size 2322154112 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q5_K_S.gguf b/LLama3.2-3B-GSM8K-R1.1.Q5_K_S.gguf new file mode 100644 index 0000000..18b8223 --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff0333e05cf9cd3b7a6aa48785970e5b993ca7d049a00a30b88297e667387be6 +size 2269512320 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q6_K.gguf b/LLama3.2-3B-GSM8K-R1.1.Q6_K.gguf new file mode 100644 index 0000000..afd896e --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e85bf157efc4e44921a19ff4225215929c0be2cdd886d4d325aa1acc065509 +size 2643853952 diff --git a/LLama3.2-3B-GSM8K-R1.1.Q8_0.gguf b/LLama3.2-3B-GSM8K-R1.1.Q8_0.gguf new file mode 100644 index 0000000..de893e4 --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4612074f6c159a020669353bfe716cd53271f2f755fd5fc06257cea8ecaa52 +size 3421899392 diff --git a/LLama3.2-3B-GSM8K-R1.1.f16.gguf b/LLama3.2-3B-GSM8K-R1.1.f16.gguf new file mode 100644 index 0000000..b583bbd --- /dev/null +++ b/LLama3.2-3B-GSM8K-R1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b521e49f6aeb3318e10614cef5d35032fd8707121a7e9ee5c94eeb223174fe0c +size 6433688192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b7ff8ca --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: PranavHarshan/LLama3.2-3B-GSM8K-R1.1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/PranavHarshan/LLama3.2-3B-GSM8K-R1.1 + + +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/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLama3.2-3B-GSM8K-R1.1-GGUF/resolve/main/LLama3.2-3B-GSM8K-R1.1.f16.gguf) | f16 | 6.5 | 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. + +