commit 594580bd9ba9a735f8f2faef541b3dd302836508 Author: ModelHub XC Date: Sun Apr 12 03:41:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..36a963c --- /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-Qwen2.5-0.5B-llamafied.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-Qwen2.5-0.5B-llamafied.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-Qwen2.5-0.5B-llamafied.IQ4_XS.gguf b/Qwen-Qwen2.5-0.5B-llamafied.IQ4_XS.gguf new file mode 100644 index 0000000..ff06c35 --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0353b513653f287173278b1f4ffb01da7b12dbb13fc2bacf0d77006c4089842 +size 351532896 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q2_K.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q2_K.gguf new file mode 100644 index 0000000..8c7d431 --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98961ec4666ef2b8149854cf75974e9878b734dee5d341ac304c7a1755a4ed25 +size 338695008 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_L.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_L.gguf new file mode 100644 index 0000000..e7e9f09 --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9afcca153590a03b6a8425bed5c875f4208e521def5a900741be92f72c7c1575 +size 369445728 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_M.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_M.gguf new file mode 100644 index 0000000..b081673 --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5439b7fa340f773ccd89d4aa2d17a3dc9764c0cf390a4fb4adcafbf8be54a9cf +size 355554144 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_S.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_S.gguf new file mode 100644 index 0000000..371c24f --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9b70963cdb496721be256bad758ff758f38659cf491aa2c899419d3b1818c1 +size 338350944 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q4_0_4_4.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q4_0_4_4.gguf new file mode 100644 index 0000000..6e381b8 --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0525524e699f6b01b30c16e379af1e7043000eea01c842f677dbb215685221 +size 352242528 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q4_K_M.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q4_K_M.gguf new file mode 100644 index 0000000..39df59d --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5cb0275219802d914cea245afcd874116634fbf92944f4c20834687a01d33bb +size 397895520 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q4_K_S.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q4_K_S.gguf new file mode 100644 index 0000000..ced847c --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3d4bb210ebd4309571036daaf936f2a44a65c986ee73e5e7c7f907574ffd4d +size 385559392 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q5_K_M.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q5_K_M.gguf new file mode 100644 index 0000000..0c2a369 --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c17db5dcf2b4885c847a1650e42e821f09f96272c305f977292988f15373a70e +size 420173664 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q5_K_S.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q5_K_S.gguf new file mode 100644 index 0000000..3370c6b --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98f8aecf9baa671b37bf3763d0e7ad42809a5e3505b9aefb5642a591c5c8f88b +size 412797792 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q6_K.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q6_K.gguf new file mode 100644 index 0000000..6a89db7 --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155f02dc6a9662b8ade79d5dec6b1acac3f29d2746d91f2f59bad24e252457f8 +size 505824096 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.Q8_0.gguf b/Qwen-Qwen2.5-0.5B-llamafied.Q8_0.gguf new file mode 100644 index 0000000..d43943f --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a73f0396d8d897482fe738890a9d201125eac0fd1915acdcad2e93143936df2e +size 531155808 diff --git a/Qwen-Qwen2.5-0.5B-llamafied.f16.gguf b/Qwen-Qwen2.5-0.5B-llamafied.f16.gguf new file mode 100644 index 0000000..8e61616 --- /dev/null +++ b/Qwen-Qwen2.5-0.5B-llamafied.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d0136fe36914736534975bc3a5db7c577bc6b0632d1934159c5eb444fe5ec3 +size 994244448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7a815f2 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: llamafy/Qwen-Qwen2.5-0.5B-llamafied +language: +- zho +- eng +- fra +- spa +- por +- deu +- ita +- rus +- jpn +- kor +- vie +- tha +- ara +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/llamafy/Qwen-Qwen2.5-0.5B-llamafied + + +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/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q4_0_4_4.gguf) | Q4_0_4_4 | 0.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-Qwen2.5-0.5B-llamafied-GGUF/resolve/main/Qwen-Qwen2.5-0.5B-llamafied.f16.gguf) | f16 | 1.1 | 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. + +