commit d537de16be504b40c12a6189d82f41838d87b998 Author: ModelHub XC Date: Mon Oct 5 05:25:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Article-Llama-3.2-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1b00e6e --- /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 +Article-Llama-3.2-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Article-Llama-3.2-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Article-Llama-3.2-1B.IQ4_XS.gguf b/Article-Llama-3.2-1B.IQ4_XS.gguf new file mode 100644 index 0000000..9adf9b5 --- /dev/null +++ b/Article-Llama-3.2-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aca9c21496a73bcf2d301e950636a8ed7d135c4dcdf9714ca86ce8f086fb760 +size 748385504 diff --git a/Article-Llama-3.2-1B.Q2_K.gguf b/Article-Llama-3.2-1B.Q2_K.gguf new file mode 100644 index 0000000..0c40e8c --- /dev/null +++ b/Article-Llama-3.2-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208c8e4b8c2835d13cd54ac286158d7229d2a237dc68853fe8d46f0b640a85d0 +size 580875488 diff --git a/Article-Llama-3.2-1B.Q3_K_L.gguf b/Article-Llama-3.2-1B.Q3_K_L.gguf new file mode 100644 index 0000000..01f8aa6 --- /dev/null +++ b/Article-Llama-3.2-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73234de9dafaef69333f657da1f5cfa24f3463056e000af9d9bb7b58f98d242 +size 732525792 diff --git a/Article-Llama-3.2-1B.Q3_K_M.gguf b/Article-Llama-3.2-1B.Q3_K_M.gguf new file mode 100644 index 0000000..ec5a4b4 --- /dev/null +++ b/Article-Llama-3.2-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457e03e6c1b01ab5ca3831a6abb02f3be836e18250ed6be1741b1b27a3712165 +size 690844896 diff --git a/Article-Llama-3.2-1B.Q3_K_S.gguf b/Article-Llama-3.2-1B.Q3_K_S.gguf new file mode 100644 index 0000000..b58a12f --- /dev/null +++ b/Article-Llama-3.2-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94dc5d6d192329c32ad6206921a3eacd56a3114f513dbdd1101c590875c1e80b +size 641692896 diff --git a/Article-Llama-3.2-1B.Q4_K_M.gguf b/Article-Llama-3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..d0dccc4 --- /dev/null +++ b/Article-Llama-3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed10bdfa4cc03d9da7d8eacb5a5a9a8a023f2c221b13b48418764f2194736977 +size 807695584 diff --git a/Article-Llama-3.2-1B.Q4_K_S.gguf b/Article-Llama-3.2-1B.Q4_K_S.gguf new file mode 100644 index 0000000..3ace2d2 --- /dev/null +++ b/Article-Llama-3.2-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5487ad985d544e1af7ad8af6505bc513026a71e860da6235f25b0ff0e98bbde +size 775648480 diff --git a/Article-Llama-3.2-1B.Q5_K_M.gguf b/Article-Llama-3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..f0be805 --- /dev/null +++ b/Article-Llama-3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a587a4847d693b2d7043327738583ba1f1d045d6100496b1ffa659b37be1c81c +size 911504608 diff --git a/Article-Llama-3.2-1B.Q5_K_S.gguf b/Article-Llama-3.2-1B.Q5_K_S.gguf new file mode 100644 index 0000000..af3c704 --- /dev/null +++ b/Article-Llama-3.2-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562f3ae4930aed17833d52f73a8141099ca5bd5160506dd60ac3b8c7132c69ef +size 892564704 diff --git a/Article-Llama-3.2-1B.Q6_K.gguf b/Article-Llama-3.2-1B.Q6_K.gguf new file mode 100644 index 0000000..02ecc96 --- /dev/null +++ b/Article-Llama-3.2-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4c9a64e4efa9a64d8d36be2c50d95aa07e7e6267f6f46b1a96e20e3efd9790 +size 1021801696 diff --git a/Article-Llama-3.2-1B.Q8_0.gguf b/Article-Llama-3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..d687351 --- /dev/null +++ b/Article-Llama-3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06ce7b401818d1de8cb021ac2004d5d32e86486e7a1d1bd8214c030dd209e32 +size 1321084128 diff --git a/Article-Llama-3.2-1B.f16.gguf b/Article-Llama-3.2-1B.f16.gguf new file mode 100644 index 0000000..c87fd99 --- /dev/null +++ b/Article-Llama-3.2-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3328d2f4622e1ac0099c5dc78c59c29083f71b99090cbdfafec1e66a86db90e9 +size 2479596768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9d4ec87 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: sayandafadar/Article-Llama-3.2-1B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/sayandafadar/Article-Llama-3.2-1B + + +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/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Article-Llama-3.2-1B-GGUF/resolve/main/Article-Llama-3.2-1B.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. + +