commit 93a25214c34a3b59d0bf90b678ea40277754f60c Author: ModelHub XC Date: Thu Jul 16 15:47:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-7B-Chat-Cantonese-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..713bc60 --- /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 +Qwen-7B-Chat-Cantonese.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-7B-Chat-Cantonese.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-7B-Chat-Cantonese.IQ4_XS.gguf b/Qwen-7B-Chat-Cantonese.IQ4_XS.gguf new file mode 100644 index 0000000..93b082e --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b807de6fb7e128a9b896e89974c1d8d90e493d7b15e6f1df986e1af796f6ebf +size 4318259616 diff --git a/Qwen-7B-Chat-Cantonese.Q2_K.gguf b/Qwen-7B-Chat-Cantonese.Q2_K.gguf new file mode 100644 index 0000000..00186ee --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc73a28c2d28907a2ec4336d29ee18dec921836988a2c9f4e9fc5c35725358b2 +size 3049294240 diff --git a/Qwen-7B-Chat-Cantonese.Q3_K_L.gguf b/Qwen-7B-Chat-Cantonese.Q3_K_L.gguf new file mode 100644 index 0000000..1df4dd5 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd7bf5c9ef157b762b21337d2ce5084042e91aa61c70a61b87dde035fdc0e433 +size 4293458336 diff --git a/Qwen-7B-Chat-Cantonese.Q3_K_M.gguf b/Qwen-7B-Chat-Cantonese.Q3_K_M.gguf new file mode 100644 index 0000000..b2619b0 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1b0b1bf0a4f851558e48f7c939a9dcdae83b55ec4c7bb875d79b08944279206 +size 4057266592 diff --git a/Qwen-7B-Chat-Cantonese.Q3_K_S.gguf b/Qwen-7B-Chat-Cantonese.Q3_K_S.gguf new file mode 100644 index 0000000..27ba47c --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70101ff307a2bdd6217c24c3f5c5c30a04c16a99bb2698084ff8a8b4af843b0e +size 3569154464 diff --git a/Qwen-7B-Chat-Cantonese.Q4_K_M.gguf b/Qwen-7B-Chat-Cantonese.Q4_K_M.gguf new file mode 100644 index 0000000..da8fb25 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cea663023c6385897558ae8540d106d8a412696828d82f6d516d9727bf78f03 +size 4899219872 diff --git a/Qwen-7B-Chat-Cantonese.Q4_K_S.gguf b/Qwen-7B-Chat-Cantonese.Q4_K_S.gguf new file mode 100644 index 0000000..5a20f63 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2a796b2cf331f947ddddf3bf14843b656f2e43294c9e03e35724611e63814bb +size 4534446496 diff --git a/Qwen-7B-Chat-Cantonese.Q5_K_M.gguf b/Qwen-7B-Chat-Cantonese.Q5_K_M.gguf new file mode 100644 index 0000000..cadfda5 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e0bc346c4b5ff2371c30773b96df301b371f7b28ae70d677d84c61f6dc36279 +size 5708917152 diff --git a/Qwen-7B-Chat-Cantonese.Q5_K_S.gguf b/Qwen-7B-Chat-Cantonese.Q5_K_S.gguf new file mode 100644 index 0000000..0d79836 --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bf88ab580d5907dc45618b18bdfcbadbc97426df4e233e5e5076179ab6b5c4d +size 5399194016 diff --git a/Qwen-7B-Chat-Cantonese.Q6_K.gguf b/Qwen-7B-Chat-Cantonese.Q6_K.gguf new file mode 100644 index 0000000..cf366fa --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c766de3bb59b743b11352b33aad3f9303ba4a4c23b26ee22fe357e73e107437c +size 6341941664 diff --git a/Qwen-7B-Chat-Cantonese.Q8_0.gguf b/Qwen-7B-Chat-Cantonese.Q8_0.gguf new file mode 100644 index 0000000..998cefb --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:041f9e37821ab58a1b78d0cd092cf93b688bdb11f6ddae42a893aedca7be3fc7 +size 8211790240 diff --git a/Qwen-7B-Chat-Cantonese.f16.gguf b/Qwen-7B-Chat-Cantonese.f16.gguf new file mode 100644 index 0000000..5be781a --- /dev/null +++ b/Qwen-7B-Chat-Cantonese.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:439af19c362d72c64faffa9687e61ab3d6f49fb0c671ab54556fbf047d42996e +size 15449913760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e738679 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: stvlynn/Qwen-7B-Chat-Cantonese +datasets: +- stvlynn/Cantonese-Dialogue +language: +- zh +library_name: transformers +license: agpl-3.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Cantonese +- 廣東話 +- 粤语 +--- +## About + + + + + + +static quants of https://huggingface.co/stvlynn/Qwen-7B-Chat-Cantonese + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-7B-Chat-Cantonese-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-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/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.Q8_0.gguf) | Q8_0 | 8.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-7B-Chat-Cantonese-GGUF/resolve/main/Qwen-7B-Chat-Cantonese.f16.gguf) | f16 | 15.5 | 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. + +