commit d1f142da59f40efff3a091138f77a9da1c13c300 Author: ModelHub XC Date: Sun Jun 14 21:02:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QnA-New-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..89d1cfe --- /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 +QnA-New.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QnA-New.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QnA-New.IQ4_XS.gguf b/QnA-New.IQ4_XS.gguf new file mode 100644 index 0000000..2303801 --- /dev/null +++ b/QnA-New.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bba6380e673ec7c04eb9c28ddcc18562c17e053550e8405e42f9a81117d12c4 +size 351445600 diff --git a/QnA-New.Q2_K.gguf b/QnA-New.Q2_K.gguf new file mode 100644 index 0000000..e010cf7 --- /dev/null +++ b/QnA-New.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13839d221c50dee24521b2b9407e1a128ac7f84e46b6420a3b8ff24780348131 +size 338607712 diff --git a/QnA-New.Q3_K_L.gguf b/QnA-New.Q3_K_L.gguf new file mode 100644 index 0000000..e3c40b6 --- /dev/null +++ b/QnA-New.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fdc1aa0bfd62f76d24d7b64888447f4a8a1fe7f15c32f046f4074cd377b950f +size 369358432 diff --git a/QnA-New.Q3_K_M.gguf b/QnA-New.Q3_K_M.gguf new file mode 100644 index 0000000..c3f8c83 --- /dev/null +++ b/QnA-New.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8941ca1ad5848bde04b95d9be0e15d701687501032b4c324dff7ff00987ae27c +size 355466848 diff --git a/QnA-New.Q3_K_S.gguf b/QnA-New.Q3_K_S.gguf new file mode 100644 index 0000000..8444b96 --- /dev/null +++ b/QnA-New.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c93c88195e880cebe0d55ef0c685c7778312dce51d6c8d5deb902347966cdf3 +size 338263648 diff --git a/QnA-New.Q4_K_M.gguf b/QnA-New.Q4_K_M.gguf new file mode 100644 index 0000000..d81555f --- /dev/null +++ b/QnA-New.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6f2eeead82e7f0a8f4727437c636601530bc830cc7c1dde9c3047c9e99da90 +size 397808224 diff --git a/QnA-New.Q4_K_S.gguf b/QnA-New.Q4_K_S.gguf new file mode 100644 index 0000000..86f125f --- /dev/null +++ b/QnA-New.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7316f0cc5b34df685d685ff9338cde69ab779141b6b272e8c451300f12032eb +size 385472096 diff --git a/QnA-New.Q5_K_M.gguf b/QnA-New.Q5_K_M.gguf new file mode 100644 index 0000000..4ddca3f --- /dev/null +++ b/QnA-New.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734168887d7a974ada86ad4423a6414804d3ad4386141651e298d2aaf353ed19 +size 420086368 diff --git a/QnA-New.Q5_K_S.gguf b/QnA-New.Q5_K_S.gguf new file mode 100644 index 0000000..6784b78 --- /dev/null +++ b/QnA-New.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe2c79c27166757d87472678f27e6a2c640694848351515335617c33fcabbc5 +size 412710496 diff --git a/QnA-New.Q6_K.gguf b/QnA-New.Q6_K.gguf new file mode 100644 index 0000000..beef028 --- /dev/null +++ b/QnA-New.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0abf3a4aa298f35069e48c750f8c5a04a8be6a99298e2b00efc9173bfd9e736 +size 505736800 diff --git a/QnA-New.Q8_0.gguf b/QnA-New.Q8_0.gguf new file mode 100644 index 0000000..cc7c9a6 --- /dev/null +++ b/QnA-New.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:080a41580276758cf01221922666adefbc24385b9b3eabb6efd8682538817d20 +size 531068512 diff --git a/QnA-New.f16.gguf b/QnA-New.f16.gguf new file mode 100644 index 0000000..351d1fb --- /dev/null +++ b/QnA-New.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ed626c76d66a8dff738703858d4291dbdd4f2162f3e39f84e93a43cfaea6f7 +size 994157152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2348ef8 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: AquilaX-AI/QnA-New +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/AquilaX-AI/QnA-New + + +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/QnA-New-GGUF/resolve/main/QnA-New.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QnA-New-GGUF/resolve/main/QnA-New.f16.gguf) | f16 | 1.1 | 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. + +