commit 78d5986c62f24d83f5d0887edd6d92a2d39cad1a Author: ModelHub XC Date: Mon Apr 13 23:56:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Alfred-ToRevuelto-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e040798 --- /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 +Alfred-ToRevuelto-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Alfred-ToRevuelto-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Alfred-ToRevuelto-1.5B.IQ4_XS.gguf b/Alfred-ToRevuelto-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..3be8fc2 --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4dd1143c37577f258f1028a74d64aa424fa8e7aa7ed160c3d2e02c072da1e65 +size 902183232 diff --git a/Alfred-ToRevuelto-1.5B.Q2_K.gguf b/Alfred-ToRevuelto-1.5B.Q2_K.gguf new file mode 100644 index 0000000..3a68f91 --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88bb8a57bb298fd3fa703b12b3fcd6022e8f87b0c9752f9164ecc69ece1999b +size 676305216 diff --git a/Alfred-ToRevuelto-1.5B.Q3_K_L.gguf b/Alfred-ToRevuelto-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..430582a --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2655a1207b4f2195c6d28e6905e439abcaf8b7bb091d9e05b4337800c15026f6 +size 880163136 diff --git a/Alfred-ToRevuelto-1.5B.Q3_K_M.gguf b/Alfred-ToRevuelto-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..19ded47 --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81dae211aaee019af40380d93b6ae1d3e7b432a1251f26a5bc3e0bc17869991c +size 824179008 diff --git a/Alfred-ToRevuelto-1.5B.Q3_K_S.gguf b/Alfred-ToRevuelto-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..f84431c --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79b8c26a7011a4077648583897b6e81c18aa9aa48c9b58bc04bd926f34eda7d1 +size 760944960 diff --git a/Alfred-ToRevuelto-1.5B.Q4_K_M.gguf b/Alfred-ToRevuelto-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..2ab8fbf --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e20edfd77ef70442befea3ff7018568879f32c9bfefe34d96a98376edcd6de +size 986048832 diff --git a/Alfred-ToRevuelto-1.5B.Q4_K_S.gguf b/Alfred-ToRevuelto-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..89bb481 --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf2a3d843cb4d057074324b252cedaa79d30d7bd21926b87a2e66ba77cdaced +size 940312896 diff --git a/Alfred-ToRevuelto-1.5B.Q5_K_M.gguf b/Alfred-ToRevuelto-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..47d3b25 --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4463d3cc6f0e8e2522969940f975a8efe9241f86328f9c5fdad2d2f43c29a283 +size 1125050688 diff --git a/Alfred-ToRevuelto-1.5B.Q5_K_S.gguf b/Alfred-ToRevuelto-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..59ea799 --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43e58c2bc7f3979fe5deb78369b7ae74fa0f7690d2318417c19cc531c2581c40 +size 1098729792 diff --git a/Alfred-ToRevuelto-1.5B.Q6_K.gguf b/Alfred-ToRevuelto-1.5B.Q6_K.gguf new file mode 100644 index 0000000..9aa3598 --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:695a20a28089acf540c14933b1bba8efd92dc5d3c68cc5f4e1b3e7fd21c2a6ac +size 1272740160 diff --git a/Alfred-ToRevuelto-1.5B.Q8_0.gguf b/Alfred-ToRevuelto-1.5B.Q8_0.gguf new file mode 100644 index 0000000..d3e30a5 --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a84e280688fc3cb4cec59453c5d3382d0223f59cd971359abbcb57c1a35ec9 +size 1646573376 diff --git a/Alfred-ToRevuelto-1.5B.f16.gguf b/Alfred-ToRevuelto-1.5B.f16.gguf new file mode 100644 index 0000000..ddf798c --- /dev/null +++ b/Alfred-ToRevuelto-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3b5c142bb3786407d1c6f25acd48720b24f1f351b48a3654f6c50588e43dd03 +size 3093669696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cb1eea8 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: YeisonJ/Alfred-ToRevuelto-1.5B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/YeisonJ/Alfred-ToRevuelto-1.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Alfred-ToRevuelto-1.5B-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/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Alfred-ToRevuelto-1.5B-GGUF/resolve/main/Alfred-ToRevuelto-1.5B.f16.gguf) | f16 | 3.2 | 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. + +