commit 5e10a1fbb52fbc4b8e3e4fcdccfb9d0eab71dd4e Author: ModelHub XC Date: Mon May 25 19:57:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AskToAct-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cbde08a --- /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 +AskToAct-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AskToAct-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AskToAct-7B.IQ4_XS.gguf b/AskToAct-7B.IQ4_XS.gguf new file mode 100644 index 0000000..af575d7 --- /dev/null +++ b/AskToAct-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1895eb2790e9fa14e4cad04651a04883c30337b120334a2e7bb8bc0753ea8ff3 +size 4250299296 diff --git a/AskToAct-7B.Q2_K.gguf b/AskToAct-7B.Q2_K.gguf new file mode 100644 index 0000000..f9e7930 --- /dev/null +++ b/AskToAct-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aa33bc727d3d4ed133e4cfef876e20a0c49a30d3f08d96aac8b86b46041de7f +size 3015941024 diff --git a/AskToAct-7B.Q3_K_L.gguf b/AskToAct-7B.Q3_K_L.gguf new file mode 100644 index 0000000..f33dbc7 --- /dev/null +++ b/AskToAct-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bd2790b75d4a1aac1e026d3f608a00457522ca2cd7a560606ca60bfa0400f9a +size 4088460192 diff --git a/AskToAct-7B.Q3_K_M.gguf b/AskToAct-7B.Q3_K_M.gguf new file mode 100644 index 0000000..4e99398 --- /dev/null +++ b/AskToAct-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4647ac642330f32c9470231b456ad640ecd2b67732c9d40e4c3f6c4b16e0be56 +size 3808392096 diff --git a/AskToAct-7B.Q3_K_S.gguf b/AskToAct-7B.Q3_K_S.gguf new file mode 100644 index 0000000..b90f37c --- /dev/null +++ b/AskToAct-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80e6cb970310953c8155951670ca511d81a4534b403ceb2e0dada2c3eed5bff0 +size 3492369312 diff --git a/AskToAct-7B.Q4_K_M.gguf b/AskToAct-7B.Q4_K_M.gguf new file mode 100644 index 0000000..95076c5 --- /dev/null +++ b/AskToAct-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce802c8039fe8ba1777a4d1eeb238f4ffc4b6e24d81817e98a62ce7be3149575 +size 4683074464 diff --git a/AskToAct-7B.Q4_K_S.gguf b/AskToAct-7B.Q4_K_S.gguf new file mode 100644 index 0000000..ed5af59 --- /dev/null +++ b/AskToAct-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81da15128772c94c6f1da659dea8325a4ccc35da198471cfbb9e305a933e0450 +size 4457769888 diff --git a/AskToAct-7B.Q5_K_M.gguf b/AskToAct-7B.Q5_K_M.gguf new file mode 100644 index 0000000..2742178 --- /dev/null +++ b/AskToAct-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f433adb50d3e82e00cbc002da8d98d421c821f4f86e3657def7f6f2fd25160 +size 5444832160 diff --git a/AskToAct-7B.Q5_K_S.gguf b/AskToAct-7B.Q5_K_S.gguf new file mode 100644 index 0000000..487a5aa --- /dev/null +++ b/AskToAct-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ede2b86da6e5c6a9e59280b075729bd95b3cac551e3c8feaf0e9e594e340b39 +size 5315177376 diff --git a/AskToAct-7B.Q6_K.gguf b/AskToAct-7B.Q6_K.gguf new file mode 100644 index 0000000..b0040e0 --- /dev/null +++ b/AskToAct-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a749b32a566eaaba827fea6f99c0e50ea7cd41ef21db21017f6778a57ec80eec +size 6254199712 diff --git a/AskToAct-7B.Q8_0.gguf b/AskToAct-7B.Q8_0.gguf new file mode 100644 index 0000000..871b402 --- /dev/null +++ b/AskToAct-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d6f13c54e7ebd0689110a9b225d95195e2852838290a321065f7ed2fb0cd6dc +size 8098526112 diff --git a/AskToAct-7B.f16.gguf b/AskToAct-7B.f16.gguf new file mode 100644 index 0000000..e71b37e --- /dev/null +++ b/AskToAct-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cebdb335e3baa109be077c1f9b8a1788f768961e013fcf10645f0ba30e0767b9 +size 15237854112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c899c6b --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: NUMB1234/AskToAct-7B +datasets: +- NUMB1234/xlam-IC +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/NUMB1234/AskToAct-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/AskToAct-7B-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/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AskToAct-7B-GGUF/resolve/main/AskToAct-7B.f16.gguf) | f16 | 15.3 | 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. + +