commit 0381f6301437ec6d82ec0debe02f7fade3226816 Author: ModelHub XC Date: Fri Jul 10 18:38:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-COT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a4640a2 --- /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-COT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-COT.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-COT.IQ4_XS.gguf b/Llama-3.2-3B-COT.IQ4_XS.gguf new file mode 100644 index 0000000..ac4bca2 --- /dev/null +++ b/Llama-3.2-3B-COT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3d90a8919cc2777b995e71b9ee511d2624d0ccdf56c94c921ea3962f7f9f30 +size 1840908768 diff --git a/Llama-3.2-3B-COT.Q2_K.gguf b/Llama-3.2-3B-COT.Q2_K.gguf new file mode 100644 index 0000000..8687579 --- /dev/null +++ b/Llama-3.2-3B-COT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d89e07b80cba41ee22952cf6021715e153601b7aef447f545489197bb1cae58 +size 1363937760 diff --git a/Llama-3.2-3B-COT.Q3_K_L.gguf b/Llama-3.2-3B-COT.Q3_K_L.gguf new file mode 100644 index 0000000..cf37cef --- /dev/null +++ b/Llama-3.2-3B-COT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937e8151725e40bc3f4d33d8e761c4e73eb44eb7ce0da22a6a7a7d6f93b61b5a +size 1815349728 diff --git a/Llama-3.2-3B-COT.Q3_K_M.gguf b/Llama-3.2-3B-COT.Q3_K_M.gguf new file mode 100644 index 0000000..6f5af29 --- /dev/null +++ b/Llama-3.2-3B-COT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afe1e5f688d71f5882cec82be51de9748e6f6e2182724e6674b6bc9895ab2da9 +size 1687161312 diff --git a/Llama-3.2-3B-COT.Q3_K_S.gguf b/Llama-3.2-3B-COT.Q3_K_S.gguf new file mode 100644 index 0000000..fffb5d9 --- /dev/null +++ b/Llama-3.2-3B-COT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6dd021bca1fb08d26acbe79193bb25280174748284eef3e3a1d84242809e6e2 +size 1542851040 diff --git a/Llama-3.2-3B-COT.Q4_0_4_4.gguf b/Llama-3.2-3B-COT.Q4_0_4_4.gguf new file mode 100644 index 0000000..5ddce95 --- /dev/null +++ b/Llama-3.2-3B-COT.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feffe4b4b0f8024dc2558acc524317f62762b03bf04598b6451661fbc96de7ac +size 1917192672 diff --git a/Llama-3.2-3B-COT.Q4_K_M.gguf b/Llama-3.2-3B-COT.Q4_K_M.gguf new file mode 100644 index 0000000..e8182a4 --- /dev/null +++ b/Llama-3.2-3B-COT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321f8be7e7dc52e318227589280a240e02cdcbf4ed0fe73f78f1ccf99f22c47b +size 2019379680 diff --git a/Llama-3.2-3B-COT.Q4_K_S.gguf b/Llama-3.2-3B-COT.Q4_K_S.gguf new file mode 100644 index 0000000..94d31c7 --- /dev/null +++ b/Llama-3.2-3B-COT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e3cbb58ce19e0f1e7b5beb11279cae083106451857720d5485a4b286a591ecc +size 1928202720 diff --git a/Llama-3.2-3B-COT.Q5_K_M.gguf b/Llama-3.2-3B-COT.Q5_K_M.gguf new file mode 100644 index 0000000..df1763d --- /dev/null +++ b/Llama-3.2-3B-COT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a6c348a7e323a0814ea2c0d2b5209b2e09257194018c2cde43e2f0f101e7540 +size 2322156000 diff --git a/Llama-3.2-3B-COT.Q5_K_S.gguf b/Llama-3.2-3B-COT.Q5_K_S.gguf new file mode 100644 index 0000000..8f0fdf9 --- /dev/null +++ b/Llama-3.2-3B-COT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dafc1b8b30bf68231c9a1076000d3ee3d049c607b29f4cedcd4abe9c341bfdd7 +size 2269514208 diff --git a/Llama-3.2-3B-COT.Q6_K.gguf b/Llama-3.2-3B-COT.Q6_K.gguf new file mode 100644 index 0000000..4efd0d7 --- /dev/null +++ b/Llama-3.2-3B-COT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc5a43cb5b52f314594b5cd633fc60134452d8fb671b26b4e28c6a2b4e7510c8 +size 2643855840 diff --git a/Llama-3.2-3B-COT.Q8_0.gguf b/Llama-3.2-3B-COT.Q8_0.gguf new file mode 100644 index 0000000..d936d27 --- /dev/null +++ b/Llama-3.2-3B-COT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fe560fe9f3010ed32a0ee0702d09f82caa877e9b02f1a8fb4d062f80713f85b +size 3421901280 diff --git a/Llama-3.2-3B-COT.f16.gguf b/Llama-3.2-3B-COT.f16.gguf new file mode 100644 index 0000000..54c7237 --- /dev/null +++ b/Llama-3.2-3B-COT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff2c79c737bd096809fa68774dbd24804559805e137ed07680870305952b0dc4 +size 6433690080 diff --git a/README.md b/README.md new file mode 100644 index 0000000..46db2ac --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: ericflo/Llama-3.2-3B-COT +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- llama-3.2 +- thought-chain +- instruction-finetuning +- transformers +--- +## About + + + + + + +static quants of https://huggingface.co/ericflo/Llama-3.2-3B-COT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-COT-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-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-COT-GGUF/resolve/main/Llama-3.2-3B-COT.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +