commit 171c64bcc0d711cd251fa403f88ea145ca8b81e3 Author: ModelHub XC Date: Sun Sep 20 18:44:26 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-1B-Instruct-KAI-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..af18f95 --- /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-Instruct-KAI.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-Instruct-KAI.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-1B-Instruct-KAI.IQ4_XS.gguf b/Llama3.2-1B-Instruct-KAI.IQ4_XS.gguf new file mode 100644 index 0000000..a0d1bb6 --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8fa8fcc4248d7671b8073482e3f80578bb7fa8726d35ea54d5908ae088b246 +size 748381280 diff --git a/Llama3.2-1B-Instruct-KAI.Q2_K.gguf b/Llama3.2-1B-Instruct-KAI.Q2_K.gguf new file mode 100644 index 0000000..342b662 --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e997f97d21e6858cefc4a170a3651d0ba14f96cc104c5338119c70f39a5514af +size 580871264 diff --git a/Llama3.2-1B-Instruct-KAI.Q3_K_L.gguf b/Llama3.2-1B-Instruct-KAI.Q3_K_L.gguf new file mode 100644 index 0000000..9b9d48e --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:170383d4d477144f37bd99bdda519489c2f8f3bffbd5307920d273b0c7ccde92 +size 732521568 diff --git a/Llama3.2-1B-Instruct-KAI.Q3_K_M.gguf b/Llama3.2-1B-Instruct-KAI.Q3_K_M.gguf new file mode 100644 index 0000000..54c173f --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dee5c7d43a862fc0c4258442e826e2f3fbac6f1dd6adb1e9950a88906f3f5a4 +size 690840672 diff --git a/Llama3.2-1B-Instruct-KAI.Q3_K_S.gguf b/Llama3.2-1B-Instruct-KAI.Q3_K_S.gguf new file mode 100644 index 0000000..8e81d53 --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4adc86996af85ceaf4a0a5e091545894384476ace687e19769547b07fe1616 +size 641688672 diff --git a/Llama3.2-1B-Instruct-KAI.Q4_K_M.gguf b/Llama3.2-1B-Instruct-KAI.Q4_K_M.gguf new file mode 100644 index 0000000..ab6f8d5 --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21971a7f55ab894356a9135e2cf88a8fe35f746605205602b01858db6a0caf1a +size 807691360 diff --git a/Llama3.2-1B-Instruct-KAI.Q4_K_S.gguf b/Llama3.2-1B-Instruct-KAI.Q4_K_S.gguf new file mode 100644 index 0000000..ad81460 --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe7f2d4ae5ab0cc107aa59e555b9fab4ca5c1a21b1fc084812c632b7453fba4 +size 775644256 diff --git a/Llama3.2-1B-Instruct-KAI.Q5_K_M.gguf b/Llama3.2-1B-Instruct-KAI.Q5_K_M.gguf new file mode 100644 index 0000000..89b9df3 --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97407cf10529083488cb56e76f3c64d58c65afcd462190c072faf68fff55361 +size 911500384 diff --git a/Llama3.2-1B-Instruct-KAI.Q5_K_S.gguf b/Llama3.2-1B-Instruct-KAI.Q5_K_S.gguf new file mode 100644 index 0000000..a33c980 --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:600f050b6b9f1b66dc84d0c5ca1e01f19276e2c351dd8bad2391d2460ab4a034 +size 892560480 diff --git a/Llama3.2-1B-Instruct-KAI.Q6_K.gguf b/Llama3.2-1B-Instruct-KAI.Q6_K.gguf new file mode 100644 index 0000000..7a7dd3a --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b0bf0f6c9a055cc52eecf9b94df693b6f817d49622b17f5254772db74319a28 +size 1021797472 diff --git a/Llama3.2-1B-Instruct-KAI.Q8_0.gguf b/Llama3.2-1B-Instruct-KAI.Q8_0.gguf new file mode 100644 index 0000000..49939cf --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:275a13f8635f121a74b60a1a4a718ccc2fdb536258f97dd27475c4f6e05fdfb8 +size 1321079904 diff --git a/Llama3.2-1B-Instruct-KAI.f16.gguf b/Llama3.2-1B-Instruct-KAI.f16.gguf new file mode 100644 index 0000000..2ba8622 --- /dev/null +++ b/Llama3.2-1B-Instruct-KAI.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb79a70162eca51c57df5dd8837beac2faf1d408707876f70bfed9eb2d1a7e89 +size 2479592544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e09a149 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: kiki-ailab/Llama3.2-1B-Instruct-KAI +language: +- vi +library_name: transformers +license: other +license_link: https://huggingface.co/kiki-ailab/Llama3.2-1B-Instruct-KAI/blob/main/LICENSE.txt +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/kiki-ailab/Llama3.2-1B-Instruct-KAI + + +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/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-Instruct-KAI-GGUF/resolve/main/Llama3.2-1B-Instruct-KAI.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. + +