commit d2af705e05d4a63b7f177f09c3ff5e550ac0eada Author: ModelHub XC Date: Tue Jun 16 19:36:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/granite-3.1-8b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a2ab4bf --- /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 +granite-3.1-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5874c2c --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: ibm-granite/granite-3.1-8b-instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- language +- granite-3.1 +--- +## About + + + + + + +static quants of https://huggingface.co/ibm-granite/granite-3.1-8b-instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/granite-3.1-8b-instruct-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/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/granite-3.1-8b-instruct-GGUF/resolve/main/granite-3.1-8b-instruct.f16.gguf) | f16 | 16.4 | 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. + + diff --git a/granite-3.1-8b-instruct.IQ4_XS.gguf b/granite-3.1-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..34121ab --- /dev/null +++ b/granite-3.1-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0dcc94049734e380a01d3e52a3f0ac23bed6543c364adcc80fa88b3bc875c33 +size 4469033952 diff --git a/granite-3.1-8b-instruct.Q2_K.gguf b/granite-3.1-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..28786e6 --- /dev/null +++ b/granite-3.1-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17c8440efc82e54a08f2c6778618094eb9e0e26c3784cb3c2bd14362a99c5d76 +size 3103591392 diff --git a/granite-3.1-8b-instruct.Q3_K_L.gguf b/granite-3.1-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c98dc81 --- /dev/null +++ b/granite-3.1-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c486c48909c8eee68cb04b64fe7573e7a7cd3ed019ccada56047559a201e0cba +size 4349430752 diff --git a/granite-3.1-8b-instruct.Q3_K_M.gguf b/granite-3.1-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..d9091fb --- /dev/null +++ b/granite-3.1-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a51060778390d0d280f9979d7bb181b5c80551a7a7838741ef9cdd913c2bda5 +size 3996584928 diff --git a/granite-3.1-8b-instruct.Q3_K_S.gguf b/granite-3.1-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..e8dda1e --- /dev/null +++ b/granite-3.1-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5caab871f19b3209b0370a81a2678adeed59d6573597544657e3723fc24afae4 +size 3592489952 diff --git a/granite-3.1-8b-instruct.Q4_K_M.gguf b/granite-3.1-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..fa50c02 --- /dev/null +++ b/granite-3.1-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a5416ebf0c326547bdaea4efc87e5d447f4d15b2bd9d3c0256ed5342927ad8d +size 4942859232 diff --git a/granite-3.1-8b-instruct.Q4_K_S.gguf b/granite-3.1-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c4f2de3 --- /dev/null +++ b/granite-3.1-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b5d82185d25a5225a5544593de98c0663127bd438c1aa8c01f52d34b8e04d64 +size 4685761504 diff --git a/granite-3.1-8b-instruct.Q5_K_M.gguf b/granite-3.1-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..90e902e --- /dev/null +++ b/granite-3.1-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37dbf7d9d156fd5aa38baf544c959a4a53189aa0f20bfeda0219cfe1474af498 +size 5797448672 diff --git a/granite-3.1-8b-instruct.Q5_K_S.gguf b/granite-3.1-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d7a25fa --- /dev/null +++ b/granite-3.1-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195041facd0e9c228d8b9db3b00b71aef209ae30353bf14d3855554de913a5f6 +size 5647043552 diff --git a/granite-3.1-8b-instruct.Q6_K.gguf b/granite-3.1-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..b4586ef --- /dev/null +++ b/granite-3.1-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8397adc265fee63bb49fead80fa59cb37b216ef1870568cdb5b6003d7cd5376 +size 6705449952 diff --git a/granite-3.1-8b-instruct.Q8_0.gguf b/granite-3.1-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..f248f57 --- /dev/null +++ b/granite-3.1-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39fceb3e9cb2527c0fe7c68d129621249f42f1f22c6cdb124dfb74db22cf5c51 +size 8684246912 diff --git a/granite-3.1-8b-instruct.f16.gguf b/granite-3.1-8b-instruct.f16.gguf new file mode 100644 index 0000000..523dfee --- /dev/null +++ b/granite-3.1-8b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f501358920ae651a55d0aa0bae35ca9fcd767f1fad95f23a33e04f29a05f906 +size 16344106112