commit 747c1f03320447fbd4d49f292cfedc567780e958 Author: ModelHub XC Date: Thu Sep 17 23:10:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen-aid-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..73ee35b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +qwen-aid-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen-aid-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..eeb45d8 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: n1ra/qwen-aid-v2 +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- autotrain +- text-generation-inference +- text-generation +- peft +--- +## About + + + + + + +static quants of https://huggingface.co/n1ra/qwen-aid-v2 + + +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/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.IQ3_XS.gguf) | IQ3_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.IQ3_S.gguf) | IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.IQ3_M.gguf) | IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen-aid-v2-GGUF/resolve/main/qwen-aid-v2.f16.gguf) | f16 | 3.2 | 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/qwen-aid-v2.IQ3_M.gguf b/qwen-aid-v2.IQ3_M.gguf new file mode 100644 index 0000000..7ab413a --- /dev/null +++ b/qwen-aid-v2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18ff0e6819d83c3e1f38b339a1ecba75e592258b19131c05f6412b7080ef48d +size 776289472 diff --git a/qwen-aid-v2.IQ3_S.gguf b/qwen-aid-v2.IQ3_S.gguf new file mode 100644 index 0000000..edb769c --- /dev/null +++ b/qwen-aid-v2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f4dcec889f436ea729a4b0ac4733ea5fe7e9a665920fe0ed45c43310c9b0ec +size 762032320 diff --git a/qwen-aid-v2.IQ3_XS.gguf b/qwen-aid-v2.IQ3_XS.gguf new file mode 100644 index 0000000..50246fb --- /dev/null +++ b/qwen-aid-v2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bff672b51b1efcd69ec03cc9464c78d665753ea75083a76b9ec67a7e78dc5de7 +size 731324608 diff --git a/qwen-aid-v2.IQ4_XS.gguf b/qwen-aid-v2.IQ4_XS.gguf new file mode 100644 index 0000000..a4c5f6d --- /dev/null +++ b/qwen-aid-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07da3eb75b478ccfdb99245abbd276fedce861a7303272e0174c2982add3a8a2 +size 901808320 diff --git a/qwen-aid-v2.Q2_K.gguf b/qwen-aid-v2.Q2_K.gguf new file mode 100644 index 0000000..0597685 --- /dev/null +++ b/qwen-aid-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b1414698dccf53e7df69e00a772f2ebac9f4d098b7698a82adba14c11ac979b +size 675930304 diff --git a/qwen-aid-v2.Q3_K_L.gguf b/qwen-aid-v2.Q3_K_L.gguf new file mode 100644 index 0000000..9ec8f87 --- /dev/null +++ b/qwen-aid-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41dd628bb3971347b6ac3496f93b01767f69beb1a850dd71fd90dfc605333d3a +size 879788224 diff --git a/qwen-aid-v2.Q3_K_M.gguf b/qwen-aid-v2.Q3_K_M.gguf new file mode 100644 index 0000000..d655b10 --- /dev/null +++ b/qwen-aid-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ce4a3569d056dec5a73e7f54a507754284a9c78d511e45e31b4e270431077a +size 823804096 diff --git a/qwen-aid-v2.Q3_K_S.gguf b/qwen-aid-v2.Q3_K_S.gguf new file mode 100644 index 0000000..9e4b3de --- /dev/null +++ b/qwen-aid-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc5d5854dbe5ff322be845032d3719be214451daacd0eaa260eccc0c3f691c5 +size 760570048 diff --git a/qwen-aid-v2.Q4_K_M.gguf b/qwen-aid-v2.Q4_K_M.gguf new file mode 100644 index 0000000..f9466f3 --- /dev/null +++ b/qwen-aid-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec5ba17557d0b2e2037e074e5964290406074311ac5963825a779f349f37b14 +size 985673920 diff --git a/qwen-aid-v2.Q4_K_S.gguf b/qwen-aid-v2.Q4_K_S.gguf new file mode 100644 index 0000000..86dafb5 --- /dev/null +++ b/qwen-aid-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcca50cecfa601966d3c84edaedce2fa0511d949d19664122a50f2cc0312d871 +size 939937984 diff --git a/qwen-aid-v2.Q5_K_M.gguf b/qwen-aid-v2.Q5_K_M.gguf new file mode 100644 index 0000000..aeacdd9 --- /dev/null +++ b/qwen-aid-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add7a9fc45681916798c6c22441420452d52716a418e50a6e8c4d154d2d24b9e +size 1124675776 diff --git a/qwen-aid-v2.Q5_K_S.gguf b/qwen-aid-v2.Q5_K_S.gguf new file mode 100644 index 0000000..659d173 --- /dev/null +++ b/qwen-aid-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f269fcfedeb427541f6bee6193514124ef7be197d167c3d22e1b71ed3d24d6 +size 1098354880 diff --git a/qwen-aid-v2.Q6_K.gguf b/qwen-aid-v2.Q6_K.gguf new file mode 100644 index 0000000..b3a70be --- /dev/null +++ b/qwen-aid-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494de19863fb4593d2b2698e9d2d7c85171ad64f492c99c939e9744502c4a1ad +size 1272365248 diff --git a/qwen-aid-v2.Q8_0.gguf b/qwen-aid-v2.Q8_0.gguf new file mode 100644 index 0000000..e794955 --- /dev/null +++ b/qwen-aid-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5acea6d06677bc53b8da1c98bf85147f9e328d930ecf9ae248d959a7279307f +size 1646090560 diff --git a/qwen-aid-v2.f16.gguf b/qwen-aid-v2.f16.gguf new file mode 100644 index 0000000..f0d7c07 --- /dev/null +++ b/qwen-aid-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:817845b99119a2a012da34a8653feab624a3cf076963d63a9aaef056da6967d1 +size 3092769280