commit 4fe00e7ecf0002d025097dbabb29cb92d1db8342 Author: ModelHub XC Date: Mon Sep 21 05:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-ASR-1.7B-Persian-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6fa3f94 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Qwen3-ASR-1.7B-Persian.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-ASR-1.7B-Persian.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-ASR-1.7B-Persian.IQ4_XS.gguf b/Qwen3-ASR-1.7B-Persian.IQ4_XS.gguf new file mode 100644 index 0000000..fd26846 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d13c258f78755ebcea77b0c3204912dae9f70694767b21344abbf8fb39bf5a5 +size 1016277440 diff --git a/Qwen3-ASR-1.7B-Persian.Q2_K.gguf b/Qwen3-ASR-1.7B-Persian.Q2_K.gguf new file mode 100644 index 0000000..37a2c44 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bef4e9c94e32cf6a666bf78601e295cedaa0592cc66904f11bc7a86feca40de8 +size 777791936 diff --git a/Qwen3-ASR-1.7B-Persian.Q3_K_L.gguf b/Qwen3-ASR-1.7B-Persian.Q3_K_L.gguf new file mode 100644 index 0000000..6d75582 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5770b0774cc3789f8a8ce2ec3e2f2910b516323f894c8f5ada092f505cc32977 +size 1003497920 diff --git a/Qwen3-ASR-1.7B-Persian.Q3_K_M.gguf b/Qwen3-ASR-1.7B-Persian.Q3_K_M.gguf new file mode 100644 index 0000000..fdab52a --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8395718fdcc728f506c5aee03c9b385a4c8ab0f9045d7e4fe81ce34dc66659c4 +size 939534784 diff --git a/Qwen3-ASR-1.7B-Persian.Q3_K_S.gguf b/Qwen3-ASR-1.7B-Persian.Q3_K_S.gguf new file mode 100644 index 0000000..701a18c --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b19b0ef8c0851ebd32a6ae5bee57f20536c8aed779b300e6ed919de6b79caca +size 867248576 diff --git a/Qwen3-ASR-1.7B-Persian.Q4_K_M.gguf b/Qwen3-ASR-1.7B-Persian.Q4_K_M.gguf new file mode 100644 index 0000000..5c6c659 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0810ab59c92a1e75214ba86002cdcd8f667b8b9c29f61ed1a24b8e789aa4213 +size 1107405248 diff --git a/Qwen3-ASR-1.7B-Persian.Q4_K_S.gguf b/Qwen3-ASR-1.7B-Persian.Q4_K_S.gguf new file mode 100644 index 0000000..a2c8748 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ae415b61e1c0614cc6ba06ae240fbb4ea4b557f9e58a07a2ce87e6c6d5914c +size 1060186560 diff --git a/Qwen3-ASR-1.7B-Persian.Q5_K_M.gguf b/Qwen3-ASR-1.7B-Persian.Q5_K_M.gguf new file mode 100644 index 0000000..3e2fdb1 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf569c2145334c1a6ea15879ed4a5f28231a598fdb3aa7f5772fa9ec0eee317 +size 1257875904 diff --git a/Qwen3-ASR-1.7B-Persian.Q5_K_S.gguf b/Qwen3-ASR-1.7B-Persian.Q5_K_S.gguf new file mode 100644 index 0000000..8e9bfdd --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94b7754edd22f564ea7b0c015d8ac52e256cc881fdfe8e1c3310d23b245767e +size 1230580160 diff --git a/Qwen3-ASR-1.7B-Persian.Q6_K.gguf b/Qwen3-ASR-1.7B-Persian.Q6_K.gguf new file mode 100644 index 0000000..89277cf --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7f63a18896312c2a14c27e714d7f87b0f5174728bf4223d975f9ee378dcf34c +size 1417750976 diff --git a/Qwen3-ASR-1.7B-Persian.Q8_0.gguf b/Qwen3-ASR-1.7B-Persian.Q8_0.gguf new file mode 100644 index 0000000..b18e655 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e647d154a0fc781ebca1588296e8b254d5702f27e3da90d6dfad45a8506a0396 +size 1834422720 diff --git a/Qwen3-ASR-1.7B-Persian.f16.gguf b/Qwen3-ASR-1.7B-Persian.f16.gguf new file mode 100644 index 0000000..ade2df6 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75bf5a81788b53cabf50765b01733f5316d2bfbd7ef04293123292543847868c +size 3447345600 diff --git a/Qwen3-ASR-1.7B-Persian.mmproj-Q8_0.gguf b/Qwen3-ASR-1.7B-Persian.mmproj-Q8_0.gguf new file mode 100644 index 0000000..757fa46 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7690c8f0654f73b8c4198892fb318c6734ceb9f11c0e8566e19118ec81c3d81 +size 355709376 diff --git a/Qwen3-ASR-1.7B-Persian.mmproj-f16.gguf b/Qwen3-ASR-1.7B-Persian.mmproj-f16.gguf new file mode 100644 index 0000000..c39df16 --- /dev/null +++ b/Qwen3-ASR-1.7B-Persian.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087be2bd8f90694ea684c062d959bd4b8b57b8984179fdff68535a3d9a171719 +size 641774016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6bf1aff --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Neurai/Qwen3-ASR-1.7B-Persian +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Neurai/Qwen3-ASR-1.7B-Persian + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-ASR-1.7B-Persian-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/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.mmproj-f16.gguf) | mmproj-f16 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-ASR-1.7B-Persian-GGUF/resolve/main/Qwen3-ASR-1.7B-Persian.f16.gguf) | f16 | 3.5 | 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. + +