commit e106b0955ee37f19c5857e3e8749b9833974ba09 Author: ModelHub XC Date: Tue May 5 21:57:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-3B-Base-DataMerged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fe58f10 --- /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-Base-DataMerged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Base-DataMerged.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-3B-Base-DataMerged.IQ4_XS.gguf b/Llama3.2-3B-Base-DataMerged.IQ4_XS.gguf new file mode 100644 index 0000000..eefd5f8 --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c58b1603ff964a9433f94dad1e6e0108af1fd3e6fd1cf67cbcaf9eebd40701 +size 1840903456 diff --git a/Llama3.2-3B-Base-DataMerged.Q2_K.gguf b/Llama3.2-3B-Base-DataMerged.Q2_K.gguf new file mode 100644 index 0000000..18e72db --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac211987d8bb1ebaa541422f59d4ed75ff8cc565f47522fed28ff528064d086b +size 1363932448 diff --git a/Llama3.2-3B-Base-DataMerged.Q3_K_L.gguf b/Llama3.2-3B-Base-DataMerged.Q3_K_L.gguf new file mode 100644 index 0000000..2d7d48c --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4bc05380ddc1878de9322d17258783de65425f8bf2772897795c9b13ab9c4fa +size 1815344416 diff --git a/Llama3.2-3B-Base-DataMerged.Q3_K_M.gguf b/Llama3.2-3B-Base-DataMerged.Q3_K_M.gguf new file mode 100644 index 0000000..853e35c --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d9c722cd9197b235c3905832a1f6c46fc7e652fc4973a1205938e25a48e09e +size 1687156000 diff --git a/Llama3.2-3B-Base-DataMerged.Q3_K_S.gguf b/Llama3.2-3B-Base-DataMerged.Q3_K_S.gguf new file mode 100644 index 0000000..6af19e7 --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1695b81c12d7b7b65ac663b10fbd3df1703f1346d1a24290184dd794e427c24 +size 1542845728 diff --git a/Llama3.2-3B-Base-DataMerged.Q4_K_M.gguf b/Llama3.2-3B-Base-DataMerged.Q4_K_M.gguf new file mode 100644 index 0000000..8221885 --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73b3d4c8f869e0ac7bc35001db7c50a491ffec30ce3d64af02b05bb8018964ac +size 2019374368 diff --git a/Llama3.2-3B-Base-DataMerged.Q4_K_S.gguf b/Llama3.2-3B-Base-DataMerged.Q4_K_S.gguf new file mode 100644 index 0000000..385b775 --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ada75a25ed6c0ba6239a9395237626cffa5fee44ca00f65dd1b996603cd8cbd +size 1928197408 diff --git a/Llama3.2-3B-Base-DataMerged.Q5_K_M.gguf b/Llama3.2-3B-Base-DataMerged.Q5_K_M.gguf new file mode 100644 index 0000000..6bec651 --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf456015edf806f2f50d4c30849eb978998bb1bac5365b7822c680219daf6a9 +size 2322150688 diff --git a/Llama3.2-3B-Base-DataMerged.Q5_K_S.gguf b/Llama3.2-3B-Base-DataMerged.Q5_K_S.gguf new file mode 100644 index 0000000..94415fc --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4b5d72a3f8ee035e03a2920b29309df2711c100129b7a72e24aa5569788441 +size 2269508896 diff --git a/Llama3.2-3B-Base-DataMerged.Q6_K.gguf b/Llama3.2-3B-Base-DataMerged.Q6_K.gguf new file mode 100644 index 0000000..878c36b --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:666ae9815323304cfb20913ab0d92059507a5fa05bb5dff85f0493c62d065437 +size 2643850528 diff --git a/Llama3.2-3B-Base-DataMerged.Q8_0.gguf b/Llama3.2-3B-Base-DataMerged.Q8_0.gguf new file mode 100644 index 0000000..c1f2c5c --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9595d440f55eda8eb8e095249c984415ae4e1c25ffd9faf18fd9c59a5c5c3f6 +size 3421895968 diff --git a/Llama3.2-3B-Base-DataMerged.f16.gguf b/Llama3.2-3B-Base-DataMerged.f16.gguf new file mode 100644 index 0000000..f57fee3 --- /dev/null +++ b/Llama3.2-3B-Base-DataMerged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1da195309c6da1174c57d726f70db5d6dd15ebd64efcb98788fa82728f0e0b1 +size 6433684768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dc0e5fe --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: Alelcv27/Llama3.2-3B-Base-DataMerged +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Alelcv27/Llama3.2-3B-Base-DataMerged + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-3B-Base-DataMerged-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/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-3B-Base-DataMerged-GGUF/resolve/main/Llama3.2-3B-Base-DataMerged.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. + +