commit e6cea7c06237ef8712dee7536871da16bafb1651 Author: ModelHub XC Date: Sun Aug 16 10:53:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Sonexa-Assistant-Qwen2.5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..123def1 --- /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 +Sonexa-Assistant-Qwen2.5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Sonexa-Assistant-Qwen2.5.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..40c29b5 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Cartik/Sonexa-Assistant-Qwen2.5 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Cartik/Sonexa-Assistant-Qwen2.5 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Sonexa-Assistant-Qwen2.5-GGUF).*** + +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/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Sonexa-Assistant-Qwen2.5-GGUF/resolve/main/Sonexa-Assistant-Qwen2.5.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. + + diff --git a/Sonexa-Assistant-Qwen2.5.IQ4_XS.gguf b/Sonexa-Assistant-Qwen2.5.IQ4_XS.gguf new file mode 100644 index 0000000..25c18d1 --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c695fb6426354f4df81157015fb105e89a9a0e1b80524ed66d3693a00f83ec8 +size 351181536 diff --git a/Sonexa-Assistant-Qwen2.5.Q2_K.gguf b/Sonexa-Assistant-Qwen2.5.Q2_K.gguf new file mode 100644 index 0000000..28bca3b --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f850dff1b23ce0c436e8b0b3f4cc5fb2f94a9b58b83472538742aa2a7a6fdf7 +size 338343648 diff --git a/Sonexa-Assistant-Qwen2.5.Q3_K_L.gguf b/Sonexa-Assistant-Qwen2.5.Q3_K_L.gguf new file mode 100644 index 0000000..fdd03f1 --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ff2bdaf3c00f64a4b24436082d3c0abcd1dbe9176d07e580dac6928bbd1f83 +size 369094368 diff --git a/Sonexa-Assistant-Qwen2.5.Q3_K_M.gguf b/Sonexa-Assistant-Qwen2.5.Q3_K_M.gguf new file mode 100644 index 0000000..3d7eb7b --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3268be5c6f0afa40ebbd569749fa225154c2cf14d17365a093957823cc21ffbc +size 355202784 diff --git a/Sonexa-Assistant-Qwen2.5.Q3_K_S.gguf b/Sonexa-Assistant-Qwen2.5.Q3_K_S.gguf new file mode 100644 index 0000000..0116de6 --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52638d0fc541bdb9ff7467411edfff08ac88f3bf249dc9424d6298417441261f +size 337999584 diff --git a/Sonexa-Assistant-Qwen2.5.Q4_K_M.gguf b/Sonexa-Assistant-Qwen2.5.Q4_K_M.gguf new file mode 100644 index 0000000..ce1651a --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f588013dc118a9c2ec70d15d19afb4b51aeab527dfa410a148e2ca02128dd77 +size 397544160 diff --git a/Sonexa-Assistant-Qwen2.5.Q4_K_S.gguf b/Sonexa-Assistant-Qwen2.5.Q4_K_S.gguf new file mode 100644 index 0000000..e9bccf1 --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bef5bca5d514fae9f4e6a022e4e668424bdb36d413bfd2656d59be5c9755361 +size 385208032 diff --git a/Sonexa-Assistant-Qwen2.5.Q5_K_M.gguf b/Sonexa-Assistant-Qwen2.5.Q5_K_M.gguf new file mode 100644 index 0000000..62be7f2 --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6fd51c5dfd4fca045488c8a25329a2939060e22faed2d93291311787e294006 +size 419822304 diff --git a/Sonexa-Assistant-Qwen2.5.Q5_K_S.gguf b/Sonexa-Assistant-Qwen2.5.Q5_K_S.gguf new file mode 100644 index 0000000..5c489d7 --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f060351a6d9f5159d2ca8aa475a448a4ca173ebb53bec344a877954729e807 +size 412446432 diff --git a/Sonexa-Assistant-Qwen2.5.Q6_K.gguf b/Sonexa-Assistant-Qwen2.5.Q6_K.gguf new file mode 100644 index 0000000..aada5c6 --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65dbbdc401410dee3d76c5a8c949074421436d1b4d27f0e0844ae0aa46c8d63f +size 505472736 diff --git a/Sonexa-Assistant-Qwen2.5.Q8_0.gguf b/Sonexa-Assistant-Qwen2.5.Q8_0.gguf new file mode 100644 index 0000000..0a0f65f --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa582943d56a15dbe897203a213cf113dc9fa51fe55bfb1f144cc7586ae0118d +size 530804448 diff --git a/Sonexa-Assistant-Qwen2.5.f16.gguf b/Sonexa-Assistant-Qwen2.5.f16.gguf new file mode 100644 index 0000000..23a37b9 --- /dev/null +++ b/Sonexa-Assistant-Qwen2.5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92762e44b82d8ab08a38b7657651ef6c36e76558dcb5e897fd2696d61edb2c58 +size 993665440