commit 5d90930b47ed22232e399ad333593d7a9b58e521 Author: ModelHub XC Date: Mon Jul 20 00:58:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5-0.5B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1171ead --- /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 +Qwen1.5-0.5B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.5B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-0.5B-Chat.IQ4_XS.gguf b/Qwen1.5-0.5B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..3d5626b --- /dev/null +++ b/Qwen1.5-0.5B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad3f440836d47ca4c6b2dc8e3ab49601702abe6354dd3fa4e645b43d078d620 +size 381847424 diff --git a/Qwen1.5-0.5B-Chat.Q2_K.gguf b/Qwen1.5-0.5B-Chat.Q2_K.gguf new file mode 100644 index 0000000..4dcd982 --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c36194d6386788216c1964f8604c2af2082568deda4298efa7b672cb466c670e +size 298413952 diff --git a/Qwen1.5-0.5B-Chat.Q3_K_L.gguf b/Qwen1.5-0.5B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..9a99295 --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b069ace5ef4eab0b92a4a613a0a2a3cc5df8d12e2e18ce5e2e2a76f711e7295d +size 364202880 diff --git a/Qwen1.5-0.5B-Chat.Q3_K_M.gguf b/Qwen1.5-0.5B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..6b26609 --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60eb81dcad1244fd6e33dd73ec5e4f8bd8db69628e7d3fecebf13e516b77c1a8 +size 349883264 diff --git a/Qwen1.5-0.5B-Chat.Q3_K_S.gguf b/Qwen1.5-0.5B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..3f8fbcf --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74473ccbfe9cd0049a525760aeb3c9e648eb613b75d81f79c46c4cb95bbd1a0b +size 333384576 diff --git a/Qwen1.5-0.5B-Chat.Q4_K_M.gguf b/Qwen1.5-0.5B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..80a6ca8 --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f35d6cf163465be5930fd40e7f5f40199e86be25b91bb1dbccebfcd403ac233 +size 407156608 diff --git a/Qwen1.5-0.5B-Chat.Q4_K_S.gguf b/Qwen1.5-0.5B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..ab4863c --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:073c542a988d1d8cbb27c6a8d6a22fbdbaacf56d5a944a46849461d0214b1fa9 +size 396597120 diff --git a/Qwen1.5-0.5B-Chat.Q5_K_M.gguf b/Qwen1.5-0.5B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..11af3de --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a023d83761e251724e5e47b1a18d7f6741612cdcf6924391055d291366e610e2 +size 459241344 diff --git a/Qwen1.5-0.5B-Chat.Q5_K_S.gguf b/Qwen1.5-0.5B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..2530435 --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf55a0a82b2c496f430c67b0638ca5135a58cbb5412496e22010a3d5c17e16f +size 452974464 diff --git a/Qwen1.5-0.5B-Chat.Q6_K.gguf b/Qwen1.5-0.5B-Chat.Q6_K.gguf new file mode 100644 index 0000000..3e2be8a --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3fc48c24cbf2e35e17506484f007f43d1c2df7c57814dd747c783235b3c92f +size 514581376 diff --git a/Qwen1.5-0.5B-Chat.Q8_0.gguf b/Qwen1.5-0.5B-Chat.Q8_0.gguf new file mode 100644 index 0000000..0871dc3 --- /dev/null +++ b/Qwen1.5-0.5B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1db565ec49b38cead70502eebcc59cd362879df35b68158e20439424320c66 +size 664603520 diff --git a/Qwen1.5-0.5B-Chat.f16.gguf b/Qwen1.5-0.5B-Chat.f16.gguf new file mode 100644 index 0000000..e2bf582 --- /dev/null +++ b/Qwen1.5-0.5B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e43fa6fde02b028eebaeb85865e5395611cb74fa2d7d0a70fd9e11fb4dfb1e8d +size 1245334400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c19257b --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: Qwen/Qwen1.5-0.5B-Chat +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat/blob/main/LICENSE +license_name: tongyi-qianwen-research +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-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/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q5_K_M.gguf) | Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.Q8_0.gguf) | Q8_0 | 0.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.5B-Chat-GGUF/resolve/main/Qwen1.5-0.5B-Chat.f16.gguf) | f16 | 1.3 | 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. + +