commit 4a503fdfb3bd4d055b2c58fd68eae30ef58f431c Author: ModelHub XC Date: Mon Jul 20 21:17:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QwenPhi-4-0.5b-Draft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..453bca2 --- /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 +QwenPhi-4-0.5b-Draft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QwenPhi-4-0.5b-Draft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QwenPhi-4-0.5b-Draft.IQ4_XS.gguf b/QwenPhi-4-0.5b-Draft.IQ4_XS.gguf new file mode 100644 index 0000000..eb658d2 --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bfe53e2f37f7a21ad4e1e83d49d2a176e7d8b40daefde0dff1a628f7d685818 +size 350524640 diff --git a/QwenPhi-4-0.5b-Draft.Q2_K.gguf b/QwenPhi-4-0.5b-Draft.Q2_K.gguf new file mode 100644 index 0000000..597f902 --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d352b6a63da24d85c6ff954ff1a1fca59b04555f0b20505776d5639808b560 +size 337686752 diff --git a/QwenPhi-4-0.5b-Draft.Q3_K_L.gguf b/QwenPhi-4-0.5b-Draft.Q3_K_L.gguf new file mode 100644 index 0000000..1ee8967 --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19fd14f8e282de700fe13a8ef098ba4f16ccbc6491d77fd9647dcd1d189ee47 +size 368437472 diff --git a/QwenPhi-4-0.5b-Draft.Q3_K_M.gguf b/QwenPhi-4-0.5b-Draft.Q3_K_M.gguf new file mode 100644 index 0000000..35040ba --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38b3791a615aa8bae7e37f075e3b931e6829f3b774840bd599b5c963caed12b1 +size 354545888 diff --git a/QwenPhi-4-0.5b-Draft.Q3_K_S.gguf b/QwenPhi-4-0.5b-Draft.Q3_K_S.gguf new file mode 100644 index 0000000..590fc03 --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbfb1358917a206c2386e77a75912e9966debec3471191a0e0d4946cf0623d1b +size 337342688 diff --git a/QwenPhi-4-0.5b-Draft.Q4_K_M.gguf b/QwenPhi-4-0.5b-Draft.Q4_K_M.gguf new file mode 100644 index 0000000..166c812 --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3d51cce4b5a192e6c92cf4bf95ab36f7f52ffa0989ab63e575754b873e91e23 +size 408126688 diff --git a/QwenPhi-4-0.5b-Draft.Q4_K_S.gguf b/QwenPhi-4-0.5b-Draft.Q4_K_S.gguf new file mode 100644 index 0000000..97540ba --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a98509ccfe3a321df3a6d957e6d89086e4f98be0ddea4989d481f8665043dce0 +size 395790560 diff --git a/QwenPhi-4-0.5b-Draft.Q5_K_M.gguf b/QwenPhi-4-0.5b-Draft.Q5_K_M.gguf new file mode 100644 index 0000000..c7b5b85 --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c597204fcd1b21392aea756e5dba4812ff44c758ebbb1939cbeaa409778cbf5 +size 436024544 diff --git a/QwenPhi-4-0.5b-Draft.Q5_K_S.gguf b/QwenPhi-4-0.5b-Draft.Q5_K_S.gguf new file mode 100644 index 0000000..15f4da9 --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f6de9b6abdc2dea1548e048df14e25a39afeaff4136d703a3b3b5ec6abc4bd1 +size 428648672 diff --git a/QwenPhi-4-0.5b-Draft.Q6_K.gguf b/QwenPhi-4-0.5b-Draft.Q6_K.gguf new file mode 100644 index 0000000..6a08d64 --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2646327cb07be0d7207bca9cbcdde2497c7a0d49bef8bcb03ce5789b419f5f90 +size 549773536 diff --git a/QwenPhi-4-0.5b-Draft.Q8_0.gguf b/QwenPhi-4-0.5b-Draft.Q8_0.gguf new file mode 100644 index 0000000..3b84620 --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1dd1f26eaa332d8f8898f40fb6abd1860ca41ce5a916a107a8018e0cce2b6f4 +size 575105248 diff --git a/QwenPhi-4-0.5b-Draft.f16.gguf b/QwenPhi-4-0.5b-Draft.f16.gguf new file mode 100644 index 0000000..d67176b --- /dev/null +++ b/QwenPhi-4-0.5b-Draft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46447a312ac4a7d770093666ba2e2cd173b9671c0e3895bfbd4d4f95f774597d +size 1079159008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..086211f --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: rdsm/QwenPhi-4-0.5b-Draft +language: +- zho +- eng +- fra +- spa +- por +- deu +- ita +- rus +- jpn +- kor +- vie +- tha +- ara +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen +- qwen2.5 +- phi-4 +- phi +--- +## About + + + + + + +static quants of https://huggingface.co/rdsm/QwenPhi-4-0.5b-Draft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QwenPhi-4-0.5b-Draft-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/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QwenPhi-4-0.5b-Draft-GGUF/resolve/main/QwenPhi-4-0.5b-Draft.f16.gguf) | f16 | 1.2 | 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. + +