commit e88132ee45e2e163418f250f32cae7c6fe389727 Author: ModelHub XC Date: Sun Oct 4 21:12:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e3100ab --- /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 +Msii_Llama-3.2-1B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Msii_Llama-3.2-1B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Msii_Llama-3.2-1B-Instruct.IQ4_XS.gguf b/Msii_Llama-3.2-1B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..5e8a3b2 --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf692b3a0cce11f8e557952556f874acb981262a8ea9604ce4ca7ed299b12e60 +size 748384352 diff --git a/Msii_Llama-3.2-1B-Instruct.Q2_K.gguf b/Msii_Llama-3.2-1B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..4c6af45 --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc77c5360a650c587d4a533f2700fddd7f671b967b2cabd072443b4246c5363 +size 580874336 diff --git a/Msii_Llama-3.2-1B-Instruct.Q3_K_L.gguf b/Msii_Llama-3.2-1B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..434aea3 --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78350f7d548121563e0412d2c57303506287d86adff137a80459b3d543ffd454 +size 732524640 diff --git a/Msii_Llama-3.2-1B-Instruct.Q3_K_M.gguf b/Msii_Llama-3.2-1B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..9548ae4 --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6aa171e7988177ee793696fd692cdf8f997893a91d4a690e9434abb1f3da4b +size 690843744 diff --git a/Msii_Llama-3.2-1B-Instruct.Q3_K_S.gguf b/Msii_Llama-3.2-1B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..553f12f --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ece64636e7d168d937a3751d1f3282aabbafe562578d4e85d759512ed996e3 +size 641691744 diff --git a/Msii_Llama-3.2-1B-Instruct.Q4_K_M.gguf b/Msii_Llama-3.2-1B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..be25a00 --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d80bd08ad2bc8181bc9d38aeba04e84306de676e1aef55dbd84087eaf130648 +size 807694432 diff --git a/Msii_Llama-3.2-1B-Instruct.Q4_K_S.gguf b/Msii_Llama-3.2-1B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..a7e9958 --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eee0002698cce9c941cbb1a51c8fcfd6119bc0354ab978ebff98f8622971189 +size 775647328 diff --git a/Msii_Llama-3.2-1B-Instruct.Q5_K_M.gguf b/Msii_Llama-3.2-1B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..592f15a --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb4daa845918125e62a2ca8a55d2830d92f3478fd1f9604b21b3ffd33e25cd4 +size 911503456 diff --git a/Msii_Llama-3.2-1B-Instruct.Q5_K_S.gguf b/Msii_Llama-3.2-1B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..7a8b253 --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1da5a74cdf81a7ea95f87555db9d5c2fc689d8ac3b60ad05fea2de6d1109d347 +size 892563552 diff --git a/Msii_Llama-3.2-1B-Instruct.Q6_K.gguf b/Msii_Llama-3.2-1B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..17c8f41 --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:416f381a3b3f34c352a7d2f1ef2cbb5a68e7273baf28cf8a46972f3206235dda +size 1021800544 diff --git a/Msii_Llama-3.2-1B-Instruct.Q8_0.gguf b/Msii_Llama-3.2-1B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..0d6778c --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6468a2c58588e574772cc2a99336aeca92e92207471fbf6050066df09c80951d +size 1321082976 diff --git a/Msii_Llama-3.2-1B-Instruct.f16.gguf b/Msii_Llama-3.2-1B-Instruct.f16.gguf new file mode 100644 index 0000000..4a94741 --- /dev/null +++ b/Msii_Llama-3.2-1B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fdc970bb025555b5a3a050228da3a850c31a4db24cdb1ee86e4212c23089367 +size 2479595616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..15eb22d --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: anish12/Msii_Llama-3.2-1B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/anish12/Msii_Llama-3.2-1B-Instruct + + +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/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Msii_Llama-3.2-1B-Instruct-GGUF/resolve/main/Msii_Llama-3.2-1B-Instruct.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. + +