commit a3da1fdcfeda947c3330b7fb28b67ba1b9edad4b Author: ModelHub XC Date: Sat Aug 1 03:49:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-3b-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4ad509f --- /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-3.2-3b-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-3b-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5fbd3fb --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: tanliboy/llama-3.2-3b-sft +datasets: +- tanliboy/OpenHermes-2.5-reformat +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- alignment-handbook +- trl +- sft +- generated_from_trainer +- trl +- sft +- alignment-handbook +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/tanliboy/llama-3.2-3b-sft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.2-3b-sft-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3.2-3b-sft-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/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-3b-sft-GGUF/resolve/main/llama-3.2-3b-sft.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. + + diff --git a/llama-3.2-3b-sft.IQ4_XS.gguf b/llama-3.2-3b-sft.IQ4_XS.gguf new file mode 100644 index 0000000..2053fb6 --- /dev/null +++ b/llama-3.2-3b-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9edbe51662490a9cf53c66c2a91672b9fd14436eda3223105b0da6e376faf5a3 +size 1840904768 diff --git a/llama-3.2-3b-sft.Q2_K.gguf b/llama-3.2-3b-sft.Q2_K.gguf new file mode 100644 index 0000000..768a406 --- /dev/null +++ b/llama-3.2-3b-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f20222e4c1a5a376f80bfc6e245a6538928b4b84a2fd870a00c9fc3bcb0c987 +size 1363933760 diff --git a/llama-3.2-3b-sft.Q3_K_L.gguf b/llama-3.2-3b-sft.Q3_K_L.gguf new file mode 100644 index 0000000..d03c79a --- /dev/null +++ b/llama-3.2-3b-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6679a62ff903cedbaa53d8959fdff5b4a9d388e6b4e977af51578f991678ee +size 1815345728 diff --git a/llama-3.2-3b-sft.Q3_K_M.gguf b/llama-3.2-3b-sft.Q3_K_M.gguf new file mode 100644 index 0000000..990c4cb --- /dev/null +++ b/llama-3.2-3b-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c92f0c3c3633b94a93782c3f81e4f4cbf3c7ed89170d9b8fc0751f80cd343b8 +size 1687157312 diff --git a/llama-3.2-3b-sft.Q3_K_S.gguf b/llama-3.2-3b-sft.Q3_K_S.gguf new file mode 100644 index 0000000..c128e7d --- /dev/null +++ b/llama-3.2-3b-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf394690b9a463aa24296c47bc3c0114436aaad63ba9b5ddf191964b3cca5fb6 +size 1542847040 diff --git a/llama-3.2-3b-sft.Q4_K_M.gguf b/llama-3.2-3b-sft.Q4_K_M.gguf new file mode 100644 index 0000000..e562731 --- /dev/null +++ b/llama-3.2-3b-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:687d0ca244a588dcacbb04352d6b476e912f6d5e8ec597cb0360637085013a11 +size 2019375680 diff --git a/llama-3.2-3b-sft.Q4_K_S.gguf b/llama-3.2-3b-sft.Q4_K_S.gguf new file mode 100644 index 0000000..bbdd9f0 --- /dev/null +++ b/llama-3.2-3b-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8838f53ef48a17ea462acf175bc625bd4e3c5879b4f14ab32a9c8fa1a82fea9 +size 1928198720 diff --git a/llama-3.2-3b-sft.Q5_K_M.gguf b/llama-3.2-3b-sft.Q5_K_M.gguf new file mode 100644 index 0000000..5c14a1b --- /dev/null +++ b/llama-3.2-3b-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73018d3d22abf564d2970e841a8d1bba04cb71e79fb1dba486b58c990147fcf4 +size 2322152000 diff --git a/llama-3.2-3b-sft.Q5_K_S.gguf b/llama-3.2-3b-sft.Q5_K_S.gguf new file mode 100644 index 0000000..3597de5 --- /dev/null +++ b/llama-3.2-3b-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92d0c3f6ad80cd350d4f03e999346e5a4b6c9ca5b0ab47b704892823a821e61 +size 2269510208 diff --git a/llama-3.2-3b-sft.Q6_K.gguf b/llama-3.2-3b-sft.Q6_K.gguf new file mode 100644 index 0000000..08e52bf --- /dev/null +++ b/llama-3.2-3b-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a5f056cd4d0b8e0a8e59c254ccaa92d90883f058edf327d43b6e62859e1157 +size 2643851840 diff --git a/llama-3.2-3b-sft.Q8_0.gguf b/llama-3.2-3b-sft.Q8_0.gguf new file mode 100644 index 0000000..8ff4855 --- /dev/null +++ b/llama-3.2-3b-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9665ffb030f73e5a9c172137d251ff26ed102fc009655a59ac99a4e21d78237 +size 3421897280 diff --git a/llama-3.2-3b-sft.f16.gguf b/llama-3.2-3b-sft.f16.gguf new file mode 100644 index 0000000..e156ee1 --- /dev/null +++ b/llama-3.2-3b-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fb7e5f1d876e38e31c13fe6e5a4e3bb320dff1e3695e0df8e9cb3652f71d2db +size 6433686080