commit ccf8f1a1d1278ba620f021f1b7fd8f4c628c1762 Author: ModelHub XC Date: Tue Jul 7 13:06:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3b-Based-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..acb7b8b --- /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-Based-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-Based-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3b-Based-v1.IQ4_XS.gguf b/Llama-3.2-3b-Based-v1.IQ4_XS.gguf new file mode 100644 index 0000000..1b2f7eb --- /dev/null +++ b/Llama-3.2-3b-Based-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:888495f83db7cbebf6525dcedec233bdf9f8b2a0a694e069c12fd973133bdc98 +size 1840907712 diff --git a/Llama-3.2-3b-Based-v1.Q2_K.gguf b/Llama-3.2-3b-Based-v1.Q2_K.gguf new file mode 100644 index 0000000..c0eb6e5 --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eebafa482934ce7681e49f6e45fe762a7e15d7804610cde40dd1e197822332d +size 1363936704 diff --git a/Llama-3.2-3b-Based-v1.Q3_K_L.gguf b/Llama-3.2-3b-Based-v1.Q3_K_L.gguf new file mode 100644 index 0000000..5e717f6 --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c0c5ac650651aafd1ee0d1edcaee2f3c994a4a1374d2331314fd5ad5875318 +size 1815348672 diff --git a/Llama-3.2-3b-Based-v1.Q3_K_M.gguf b/Llama-3.2-3b-Based-v1.Q3_K_M.gguf new file mode 100644 index 0000000..f56a0c1 --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:608665334b8120d5e6ae3fea72d21444006484b0d3cbac6eb238afde22e9e0df +size 1687160256 diff --git a/Llama-3.2-3b-Based-v1.Q3_K_S.gguf b/Llama-3.2-3b-Based-v1.Q3_K_S.gguf new file mode 100644 index 0000000..a5a54f1 --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74df874cd065d380d7065021a0c3ffffd3ed4e9b3a6acdecbba203e69f2d56a6 +size 1542849984 diff --git a/Llama-3.2-3b-Based-v1.Q4_K_M.gguf b/Llama-3.2-3b-Based-v1.Q4_K_M.gguf new file mode 100644 index 0000000..9c6978e --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2370c0eda3e585d08c4949a6c2dfe2434afb682dc7ec309e7ab61abb791b72f2 +size 2019378624 diff --git a/Llama-3.2-3b-Based-v1.Q4_K_S.gguf b/Llama-3.2-3b-Based-v1.Q4_K_S.gguf new file mode 100644 index 0000000..53687fc --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1b0ba0625f5e78f1e66a20c15d4fa065f6873eef0820c216b337f643b884be9 +size 1928201664 diff --git a/Llama-3.2-3b-Based-v1.Q5_K_M.gguf b/Llama-3.2-3b-Based-v1.Q5_K_M.gguf new file mode 100644 index 0000000..415306f --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfa4e16a34e55a6f11ac9e27e3aa578208158eaf9472386e5c50d2bf8cd9c1e9 +size 2322154944 diff --git a/Llama-3.2-3b-Based-v1.Q5_K_S.gguf b/Llama-3.2-3b-Based-v1.Q5_K_S.gguf new file mode 100644 index 0000000..c048a45 --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ad9fe23f2c80eea8207b592eb2cd3a15c5393e83f3d23bc7f2abbe752f0426 +size 2269513152 diff --git a/Llama-3.2-3b-Based-v1.Q6_K.gguf b/Llama-3.2-3b-Based-v1.Q6_K.gguf new file mode 100644 index 0000000..a4ad483 --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc79ba0edf8dff25fd5c5c3b77af506acd5157451977663faffd2a999a07aca +size 2643854784 diff --git a/Llama-3.2-3b-Based-v1.Q8_0.gguf b/Llama-3.2-3b-Based-v1.Q8_0.gguf new file mode 100644 index 0000000..2969457 --- /dev/null +++ b/Llama-3.2-3b-Based-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42b05adc93dfcfa732e3e0b564fc472d1e6a0707384c720194f89f0885af8474 +size 3421900224 diff --git a/Llama-3.2-3b-Based-v1.f16.gguf b/Llama-3.2-3b-Based-v1.f16.gguf new file mode 100644 index 0000000..ed99d79 --- /dev/null +++ b/Llama-3.2-3b-Based-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3228a8fd6ac93bbaf578a2da81546a2415387144f1f96f0ba425804c16151fa3 +size 6433689024 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4978677 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: llm4thewin/Llama-3.2-3b-Based-v1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/llm4thewin/Llama-3.2-3b-Based-v1 + + +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-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-Based-v1-GGUF/resolve/main/Llama-3.2-3b-Based-v1.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. + +