commit be30632837638ec06efcee54bd77cc6d97182160 Author: ModelHub XC Date: Tue Jun 23 12:06:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cdb77ae --- /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-Math-gsm8k-AutoSFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Math-gsm8k-AutoSFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.IQ4_XS.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.IQ4_XS.gguf new file mode 100644 index 0000000..b2d706e --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cb2309e32d4d0f5226bf2cc46e50efdd81dc6db7059ed4ab106c308daf5f4fb +size 1840907424 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q2_K.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q2_K.gguf new file mode 100644 index 0000000..b00614e --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4afade6fd9ce57ffca20abb08f9de64b7d97e5fef877478359f637fca8101175 +size 1363936416 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_L.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_L.gguf new file mode 100644 index 0000000..8d16744 --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be5dab4f755307ac8351907947b11d68fb33cf159bb18eba4c139fd2fcf477a3 +size 1815348384 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_M.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_M.gguf new file mode 100644 index 0000000..d110db4 --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2492f23b0a46aceb0dd35985edcb560bfaa4a188cf1b94653a3eb41e2515e0b3 +size 1687159968 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_S.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_S.gguf new file mode 100644 index 0000000..4cb2772 --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e9c903dd6f642dd0297b0402b9992c5908360e5e8f47c23addea17d75b2f40f +size 1542849696 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_M.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_M.gguf new file mode 100644 index 0000000..a99853c --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41aea6e5879d81809c1bafe4fb2bf12450d6c4cea08b9f7a09d26e3fbf3a73f5 +size 2019378336 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_S.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_S.gguf new file mode 100644 index 0000000..1a4896e --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f90982d47318f7daef746a87f201ec1147d5101cfd17528f9a87ac7ee223f4 +size 1928201376 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_M.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_M.gguf new file mode 100644 index 0000000..2a69938 --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d846f5a53d452cd9b03e96e00caa39ec5e06d90f69d3303ff66bbe3127f6f5f +size 2322154656 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_S.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_S.gguf new file mode 100644 index 0000000..352c5c4 --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7244cb46d47945578398e8cff1c1950ad3f771dede61ed9d99e66c6f6f6bfa5a +size 2269512864 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q6_K.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q6_K.gguf new file mode 100644 index 0000000..ec95bb7 --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a57611d2bfbf6b91a5c335ac11c742b0f495eaa913f73082f7a9cfabc50ceb5 +size 2643854496 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.Q8_0.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q8_0.gguf new file mode 100644 index 0000000..104c422 --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6d8436ac21cc240f6d98a45cc8120f96d255e7e029a39dabd1d0a9cd831ce8 +size 3421899936 diff --git a/Llama3.2-3B-Math-gsm8k-AutoSFT.f16.gguf b/Llama3.2-3B-Math-gsm8k-AutoSFT.f16.gguf new file mode 100644 index 0000000..b422a4f --- /dev/null +++ b/Llama3.2-3B-Math-gsm8k-AutoSFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a2a220c1ff2520470f8bd1be6ec9eb4f8eaf587031ea06f97f49a47e8e0b06 +size 6433688736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4a3855f --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: theprint/Llama3.2-3B-Math-gsm8k-AutoSFT +datasets: +- openai/gsm8k +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/theprint/Llama3.2-3B-Math-gsm8k-AutoSFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-i1-GGUF +## 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-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Math-gsm8k-AutoSFT-GGUF/resolve/main/Llama3.2-3B-Math-gsm8k-AutoSFT.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. + +