commit e56f06d778f1a64702ca99f8f1d102b53a674a6f Author: ModelHub XC Date: Thu Jul 23 01:37:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5-0.4B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..34fe180 --- /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 +Qwen1.5-0.4B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-0.4B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-0.4B-Chat.IQ4_XS.gguf b/Qwen1.5-0.4B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..64fb1e2 --- /dev/null +++ b/Qwen1.5-0.4B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64e29683a382f643f13450fdf649ce34854844a77ca8e081dbbfe0bb9c3769d0 +size 271360896 diff --git a/Qwen1.5-0.4B-Chat.Q2_K.gguf b/Qwen1.5-0.4B-Chat.Q2_K.gguf new file mode 100644 index 0000000..0e1e49d --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:775fbdecbd69dadc00c3f450074f4273a8a54452cbae916ebae029f80e23ad85 +size 228393856 diff --git a/Qwen1.5-0.4B-Chat.Q3_K_L.gguf b/Qwen1.5-0.4B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..e1f32e4 --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9deba89ed8cb6811fb8dfaaf56a9efacd34b8ff513b2743cd8e0872a8654c3c6 +size 270050176 diff --git a/Qwen1.5-0.4B-Chat.Q3_K_M.gguf b/Qwen1.5-0.4B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..50b05c1 --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00754972c5916c06fedf1112ae8bc5512ca89207b164fa2002cfa079cb613cd1 +size 258220928 diff --git a/Qwen1.5-0.4B-Chat.Q3_K_S.gguf b/Qwen1.5-0.4B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..f013e6d --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d423b9081fec1ed4983d6aebe61482e2a58ea80af53208c1f46104c9ba1a4680 +size 244368256 diff --git a/Qwen1.5-0.4B-Chat.Q4_K_M.gguf b/Qwen1.5-0.4B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..47e520b --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c795194178727e7e08315c6e433a84600b7eee260af4ee03d393a3e4376049 +size 288625536 diff --git a/Qwen1.5-0.4B-Chat.Q4_K_S.gguf b/Qwen1.5-0.4B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..41cf2ee --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f920ff1e98e50e47a5bcc2ec1bbf0ccb4988d437cafe64803d8b22ddf0635f +size 279733120 diff --git a/Qwen1.5-0.4B-Chat.Q5_K_M.gguf b/Qwen1.5-0.4B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..e641719 --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9947a139d6c2c947d9a91a6a5dec085ba7db9e369920bafcebf8d1473c54a3c8 +size 315822976 diff --git a/Qwen1.5-0.4B-Chat.Q5_K_S.gguf b/Qwen1.5-0.4B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..fe9034d --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3f9ec461e7f4eb077cfc8a75b810cdee5a2da4f671da9facd8bac6de8dbc8e +size 310600576 diff --git a/Qwen1.5-0.4B-Chat.Q6_K.gguf b/Qwen1.5-0.4B-Chat.Q6_K.gguf new file mode 100644 index 0000000..57fdfb1 --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dfa02e42bd70494559f256c9cb145a9bd845375d48b5452ba245cf903fd4a83 +size 344720256 diff --git a/Qwen1.5-0.4B-Chat.Q8_0.gguf b/Qwen1.5-0.4B-Chat.Q8_0.gguf new file mode 100644 index 0000000..00ebf0c --- /dev/null +++ b/Qwen1.5-0.4B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fb0f834624d29cf235c974a370ce67dd790a0e4dca6ebe3940fccfa2c2f7b91 +size 444618624 diff --git a/Qwen1.5-0.4B-Chat.f16.gguf b/Qwen1.5-0.4B-Chat.f16.gguf new file mode 100644 index 0000000..a474008 --- /dev/null +++ b/Qwen1.5-0.4B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af800918e269fdbb5a9937ec3a9093628d25383d7c26deacdc1740388a0b6870 +size 831321984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..375ae85 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: nathanrchn/Qwen1.5-0.4B-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: [] +--- +## About + + + + + + +static quants of https://huggingface.co/nathanrchn/Qwen1.5-0.4B-Chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen1.5-0.4B-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/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q3_K_L.gguf) | Q3_K_L | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.IQ4_XS.gguf) | IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-0.4B-Chat-GGUF/resolve/main/Qwen1.5-0.4B-Chat.f16.gguf) | f16 | 0.9 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +