commit e8a5e11447872946adb0ac2d17090ec4de33d3ba Author: ModelHub XC Date: Mon Apr 20 11:35:39 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/vetta-granite-2b-v3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fffd19b --- /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 +vetta-granite-2b-v3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +vetta-granite-2b-v3.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..db87d84 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: asifdotpy/vetta-granite-2b-v3 +language: en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- granite +- fine-tuned +- interview +- ai-interviewer +- vetta +- merged +--- +## About + + + + + + + + + +static quants of https://huggingface.co/asifdotpy/vetta-granite-2b-v3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#vetta-granite-2b-v3-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/vetta-granite-2b-v3-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/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q2_K.gguf) | Q2_K | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q3_K_S.gguf) | Q3_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q3_K_M.gguf) | Q3_K_M | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q3_K_L.gguf) | Q3_K_L | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.IQ4_XS.gguf) | IQ4_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q4_K_S.gguf) | Q4_K_S | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q4_K_M.gguf) | Q4_K_M | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/vetta-granite-2b-v3-GGUF/resolve/main/vetta-granite-2b-v3.f16.gguf) | f16 | 5.2 | 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/vetta-granite-2b-v3.IQ4_XS.gguf b/vetta-granite-2b-v3.IQ4_XS.gguf new file mode 100644 index 0000000..6464049 --- /dev/null +++ b/vetta-granite-2b-v3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71378235dedef069f48100cac8d978c66f2f53b1374ab4a42e9cfc6e1bd4fb01 +size 1397018176 diff --git a/vetta-granite-2b-v3.Q2_K.gguf b/vetta-granite-2b-v3.Q2_K.gguf new file mode 100644 index 0000000..57e920e --- /dev/null +++ b/vetta-granite-2b-v3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c5a99ded66302b0fef12a585c9c2c15927d0c5413b90cb4f97267a6aca9696 +size 978243136 diff --git a/vetta-granite-2b-v3.Q3_K_L.gguf b/vetta-granite-2b-v3.Q3_K_L.gguf new file mode 100644 index 0000000..b7c6813 --- /dev/null +++ b/vetta-granite-2b-v3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6c0181d8b72a667d9015a05b9eba8faa02d549320ac44db36c580f92c8138a +size 1357368896 diff --git a/vetta-granite-2b-v3.Q3_K_M.gguf b/vetta-granite-2b-v3.Q3_K_M.gguf new file mode 100644 index 0000000..380135f --- /dev/null +++ b/vetta-granite-2b-v3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a131ce5c7cd0f2ec5ad396ac1044ec9dd290ac51c157b6c9ff16485c39ec53 +size 1251724864 diff --git a/vetta-granite-2b-v3.Q3_K_S.gguf b/vetta-granite-2b-v3.Q3_K_S.gguf new file mode 100644 index 0000000..81e9ecc --- /dev/null +++ b/vetta-granite-2b-v3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65270456b4112ae2b1c82129edaefcbab0638d5d2e7502aefad436c3e5f6062a +size 1130286656 diff --git a/vetta-granite-2b-v3.Q4_K_M.gguf b/vetta-granite-2b-v3.Q4_K_M.gguf new file mode 100644 index 0000000..7f21272 --- /dev/null +++ b/vetta-granite-2b-v3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7762b850138491cb055d59221d8a036144a65b009951a038ac96910416d61ff +size 1545293376 diff --git a/vetta-granite-2b-v3.Q4_K_S.gguf b/vetta-granite-2b-v3.Q4_K_S.gguf new file mode 100644 index 0000000..b1ea86d --- /dev/null +++ b/vetta-granite-2b-v3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee80c9b493af6d7b0219695ba204cfa5966dd0208572a784a21e407b11297827 +size 1464389184 diff --git a/vetta-granite-2b-v3.Q5_K_M.gguf b/vetta-granite-2b-v3.Q5_K_M.gguf new file mode 100644 index 0000000..fb42ba0 --- /dev/null +++ b/vetta-granite-2b-v3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0569b0772d06d2adfd73af263e8e94c5230a8b124bffa1145e9d3ca6ca24bd50 +size 1804815936 diff --git a/vetta-granite-2b-v3.Q5_K_S.gguf b/vetta-granite-2b-v3.Q5_K_S.gguf new file mode 100644 index 0000000..8e0bfb3 --- /dev/null +++ b/vetta-granite-2b-v3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f99520fdf8726ea7001cf9162d7b2758a820d84456587d1dce11d38eed3601 +size 1757466176 diff --git a/vetta-granite-2b-v3.Q6_K.gguf b/vetta-granite-2b-v3.Q6_K.gguf new file mode 100644 index 0000000..fb05662 --- /dev/null +++ b/vetta-granite-2b-v3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b49142abf6963031b25ceca16192d952dfca9f2622ec0aa445f6e75baa06976d +size 2080558656 diff --git a/vetta-granite-2b-v3.Q8_0.gguf b/vetta-granite-2b-v3.Q8_0.gguf new file mode 100644 index 0000000..abb5cf6 --- /dev/null +++ b/vetta-granite-2b-v3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0a471e61a26238d53ef138d8f204ad6b48909bab791e5fa45eeffeb3eac89e +size 2694108160 diff --git a/vetta-granite-2b-v3.f16.gguf b/vetta-granite-2b-v3.f16.gguf new file mode 100644 index 0000000..711915b --- /dev/null +++ b/vetta-granite-2b-v3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71e80328d886d9c2837bedc54f965ede425380368700faad2da5447507f14d7 +size 5069138560