commit 5174229d0410f473e51ceb33cb6c9ed245bf0159 Author: ModelHub XC Date: Tue Jun 9 10:18:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-1B-ThinkMix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..abdccca --- /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 +Llama3.2-1B-ThinkMix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-ThinkMix.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-1B-ThinkMix.IQ4_XS.gguf b/Llama3.2-1B-ThinkMix.IQ4_XS.gguf new file mode 100644 index 0000000..1adfdb8 --- /dev/null +++ b/Llama3.2-1B-ThinkMix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9c9cfe749b86a4039890843f47c0b1c766b33360bd3f70ec6c3cf9d12b1de9 +size 748385920 diff --git a/Llama3.2-1B-ThinkMix.Q2_K.gguf b/Llama3.2-1B-ThinkMix.Q2_K.gguf new file mode 100644 index 0000000..fa9295c --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d68fb5720c45ad901e8c6e0f0c103f1fcbe47e49731958592e830119d8cebce +size 580875904 diff --git a/Llama3.2-1B-ThinkMix.Q3_K_L.gguf b/Llama3.2-1B-ThinkMix.Q3_K_L.gguf new file mode 100644 index 0000000..e90b05c --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabd63e8f83fd315532cfb500d979c6f0439c09d452080a2ba3137e07f3cd1ac +size 732526208 diff --git a/Llama3.2-1B-ThinkMix.Q3_K_M.gguf b/Llama3.2-1B-ThinkMix.Q3_K_M.gguf new file mode 100644 index 0000000..a8bbc5d --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97e828bb2074c0b611b693cc2a2854d14d5d81eeddf5627c21061b10007adb4c +size 690845312 diff --git a/Llama3.2-1B-ThinkMix.Q3_K_S.gguf b/Llama3.2-1B-ThinkMix.Q3_K_S.gguf new file mode 100644 index 0000000..f89add1 --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e54bb2a3eaeb65e45e6a1546e97d3e6471f8063e5edb1677d757210be0263e9a +size 641693312 diff --git a/Llama3.2-1B-ThinkMix.Q4_K_M.gguf b/Llama3.2-1B-ThinkMix.Q4_K_M.gguf new file mode 100644 index 0000000..c325018 --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ad6a34c336b1f85016241250857d2f828f41cee1d6de981db5c7a37dc34f495 +size 807696000 diff --git a/Llama3.2-1B-ThinkMix.Q4_K_S.gguf b/Llama3.2-1B-ThinkMix.Q4_K_S.gguf new file mode 100644 index 0000000..bfc69a4 --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa74bc1c53ead1038995e118a6035c6043fde788f5f96cc72b35e0a87d700407 +size 775648896 diff --git a/Llama3.2-1B-ThinkMix.Q5_K_M.gguf b/Llama3.2-1B-ThinkMix.Q5_K_M.gguf new file mode 100644 index 0000000..06aa34e --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ecf28340194883f616299867ed5e6907f57675b13dec24b972ca11d5dcb5e1 +size 911505024 diff --git a/Llama3.2-1B-ThinkMix.Q5_K_S.gguf b/Llama3.2-1B-ThinkMix.Q5_K_S.gguf new file mode 100644 index 0000000..929b5e3 --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20c2b082b6ad2f1c40870b7e317e6c81fc6499a44bfb8f577dd68c061dc7b93a +size 892565120 diff --git a/Llama3.2-1B-ThinkMix.Q6_K.gguf b/Llama3.2-1B-ThinkMix.Q6_K.gguf new file mode 100644 index 0000000..6d7427c --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff6982879522531b633d7d20fc5f2e63a3686784c5fac3d85f7433b8855aff34 +size 1021802112 diff --git a/Llama3.2-1B-ThinkMix.Q8_0.gguf b/Llama3.2-1B-ThinkMix.Q8_0.gguf new file mode 100644 index 0000000..50b0ef4 --- /dev/null +++ b/Llama3.2-1B-ThinkMix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc831dc6ddd07c11139f78b933cfa14358159410d5cd2609d93eb1c175c7881a +size 1321084544 diff --git a/Llama3.2-1B-ThinkMix.f16.gguf b/Llama3.2-1B-ThinkMix.f16.gguf new file mode 100644 index 0000000..8144f1d --- /dev/null +++ b/Llama3.2-1B-ThinkMix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b32496c04c5d9a5c060e427bf6b6528a0a72c5812b4b100f81de66e8b9abfb +size 2479597184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e548312 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: theprint/Llama3.2-1B-ThinkMix +datasets: +- theprint/ThinkMix-GPT-0126 +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/theprint/Llama3.2-1B-ThinkMix + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-1B-ThinkMix-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-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/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-ThinkMix-GGUF/resolve/main/Llama3.2-1B-ThinkMix.f16.gguf) | f16 | 2.6 | 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. + +