commit 64eaa4889531733ee6aa76d88533de23d2da3877 Author: ModelHub XC Date: Tue Jun 16 18:38:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cf80996 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.0-1b-a400m-instruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f6c6b3a --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: ibm-granite/granite-3.0-1b-a400m-instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- language +- granite-3.0 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/ibm-granite/granite-3.0-1b-a400m-instruct + + +static quants are available at https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-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/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q2_K.gguf) | i1-Q2_K | 0.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 0.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 0.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 0.9 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 0.9 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.0-1b-a400m-instruct-i1-GGUF/resolve/main/granite-3.0-1b-a400m-instruct.i1-Q6_K.gguf) | i1-Q6_K | 1.2 | practically like static Q6_K | + +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. + + diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ1_M.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..e29469b --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6944d2d63630d2164309b2e09ec02334d09efce098ac85d3211cfbe4cce613 +size 331259200 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ1_S.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..7b7bc5b --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d940081a0758bceb5fd1365dba71359f654f62a6f2a3af528ccb0a2a425176 +size 303242560 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ2_M.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..fc42f78 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14eb7d568eedd27c9577a8d544fc8ff105938eec34201954619a93ddc65d76af +size 462101824 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ2_S.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..0924953 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a377636b1d7eaf6106b52bcc27076ee80b826b314c481041cd4aa57a586c1817 +size 424746304 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ2_XS.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..61c7101 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:481972f07b5b18a41200b19bb8480ccbedec1ed6a4970f86533387014e78ebe1 +size 416095552 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ2_XXS.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..91354ec --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0b5e563ad2ad8fd52c8a90d8616008f2a0d02432f61c0707e372af741a4a85c +size 377953600 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ3_M.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..f65741e --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a21a4fe19bfba7484eb9731678842942924b0cc5764f8d03a2edb66adec588e +size 609558240 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ3_S.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..e0ac8ef --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da80277db6cf5dc2289ff0a77e42f750c2a0e459b62c521fcf61a21cbe39726 +size 597860064 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ3_XS.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0e9feef --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:935b48ad46ce1640f64f49f5115e9818eeee7259da82ebf84c9dc9643ede08a9 +size 567779040 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ3_XXS.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..017e8b7 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd103dc2d30b1fdc906902ae7ff4bc5aa315041f475d9aa4ab1d8be612ae33f1 +size 529833280 diff --git a/granite-3.0-1b-a400m-instruct.i1-IQ4_XS.gguf b/granite-3.0-1b-a400m-instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..3d3983c --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176bc60278b03340ca45d91a24549c53a2cfdb12283259c4771fa47d3900ac85 +size 728211168 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q2_K.gguf b/granite-3.0-1b-a400m-instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..d68dc5d --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e139d7908ded11b40490ae5c42ca3b2c035bab5244d63821fd0d3942789d853c +size 512237280 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q3_K_L.gguf b/granite-3.0-1b-a400m-instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2eb0729 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36663f3d9866de2f2cd8701d55002faf72bf03c7781c62d381e02359c280e312 +size 711401184 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q3_K_M.gguf b/granite-3.0-1b-a400m-instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c54848a --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75dd7f098918c5e798a34d1a68257829e95237f831b6b920bf1bc5d18df83dc8 +size 658579168 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q3_K_S.gguf b/granite-3.0-1b-a400m-instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..795bafc --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ae9ba0224d291099fd45559fa70bc7de86e2db87e7254bb5e228133078a909 +size 597860064 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q4_0.gguf b/granite-3.0-1b-a400m-instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..8bd9276 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb07e504f7ca6c5b05190096f2d9f4e6fe58d7b6bb5ff0bdc93c1e56881a85f +size 771464928 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q4_0_4_4.gguf b/granite-3.0-1b-a400m-instruct.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..7ef4e2b --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8e493d21baefbe539be2cb908e4d87e93d028d21afd849c9385fb406bc36dec +size 768319200 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q4_0_4_8.gguf b/granite-3.0-1b-a400m-instruct.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..016923a --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57df5aba7ff3275f1ee1b6b864870287667449feee43c5fae4c1fa35cd3f9e8 +size 768319200 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q4_0_8_8.gguf b/granite-3.0-1b-a400m-instruct.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..84802c1 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0fd9d930606360dfa99d3e4ff74a79293aa0d7c9f978712c86a8c012634559d +size 768319200 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q4_K_M.gguf b/granite-3.0-1b-a400m-instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..04c9e83 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de46ec67faec3b8d2f5bdec9a0e4f811c8b0a090d1ba111b323cac95bf5f3970 +size 821845728 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q4_K_S.gguf b/granite-3.0-1b-a400m-instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c2eca80 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f316d40008c889eaf4dd25d27a55ca0b26bc8331795032da0110b21c79224f5 +size 774872800 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q5_K_M.gguf b/granite-3.0-1b-a400m-instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..19b3697 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4bfec59a932eb6b0285c176437956d75be272336de2ff56dd09cb9b733fa9ab +size 956325600 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q5_K_S.gguf b/granite-3.0-1b-a400m-instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5865b61 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21fbfd9c11be0ac2a89ddee3e66d125ccc149183d313361270e80d69ebaacd55 +size 928751328 diff --git a/granite-3.0-1b-a400m-instruct.i1-Q6_K.gguf b/granite-3.0-1b-a400m-instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..f746124 --- /dev/null +++ b/granite-3.0-1b-a400m-instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df1cc86a08c0fb9026ab45f7f20b1a2b7fb76c87bfb252eab1f1155628265830 +size 1099210464 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..5f755d1 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a92d61fb667187e1cd3834564f494ef7d650fa53c0a92aa83e93dcd4185472f +size 8362659