commit 88ac53bc8fd745adf39ab2cc64ab848cf20e1e59 Author: ModelHub XC Date: Sat Sep 26 22:15:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..16690af --- /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 +Self-Certainty-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct-MATH.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c95af4f --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: TMLR-Group-HF/Self-Certainty-Llama-3.2-3B-Instruct-MATH +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/TMLR-Group-HF/Self-Certainty-Llama-3.2-3B-Instruct-MATH + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Self-Certainty-Llama-3.2-3B-Instruct-MATH-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/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-MATH-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct-MATH.f16.gguf) | f16 | 7.3 | 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. + + diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf new file mode 100644 index 0000000..f224c2e --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c284b2c06f900fcca78ec982c34e01acd04d3dca6bf3beee9c3de7ce532d06f +size 2050220832 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf new file mode 100644 index 0000000..6f42ec7 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:366020c0509046a57957dca35dfab3b1bd5ecac29770e195e745c54194bac07e +size 1493218080 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf new file mode 100644 index 0000000..38fe8d2 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967acd026ad60723d1f4c4a4abe056e0f9fe60be41579eb8b5e9ac5d296ba513 +size 1984645920 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf new file mode 100644 index 0000000..fedfc16 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cf2f44b21c3801eb89a45fce7e0448f2a20c742508e2981ca132a31e68fde4 +size 1856457504 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf new file mode 100644 index 0000000..bd9e341 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00aaa4850d6dd8f32b83ec52c67dd1ecd3001629b95a45fbb58ad38e2bb121e6 +size 1712147232 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf new file mode 100644 index 0000000..3055cbb --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f2041ea7d3ecee3df1c9aa6758ddad475c6ba3af4c0d1d656b3efc7a71bc973 +size 2241004320 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf new file mode 100644 index 0000000..0e5fa54 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f99282b31c2b0eb911f8ad355cde80cc3f9d53eaadcf2abd0e79461bf22fd4d6 +size 2149827360 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf new file mode 100644 index 0000000..d621156 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026af76b2b80c72b3e8813f0e0d975861de842dfeec7e8a8465830092aec1175 +size 2593030944 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf new file mode 100644 index 0000000..903b0a7 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf5acd3362db2f49f5b62518f18273cd698db70394dd81c08a56963037e350c +size 2540389152 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf new file mode 100644 index 0000000..1286e05 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa8bd4e77cf6850f0570d6289003f4bc0d147dd518aa174ec2d9fa27a9182a0 +size 2967059232 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf new file mode 100644 index 0000000..b13aeca --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1386a93162685f7964dfbce488fe144bf9880c95c7cc81eb788bc7d6ba029a47 +size 3840527136 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct-MATH.f16.gguf b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.f16.gguf new file mode 100644 index 0000000..d2d660d --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct-MATH.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f704ba2978400454e42062a0b16bdc7b76cb0fb4004d7414c49bf463b4531e3 +size 7221693216