commit 6ae8652cfb05840d21cd7fba9be25d48379a5ed7 Author: ModelHub XC Date: Wed Jul 15 07:57:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..98585a0 --- /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 +Qwen2.5-0.5B-Distill-Fast.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Distill-Fast.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-0.5B-Distill-Fast.IQ4_XS.gguf b/Qwen2.5-0.5B-Distill-Fast.IQ4_XS.gguf new file mode 100644 index 0000000..e844f7e --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691cc3e49d6a0f95e2c601e195ae593dff691e1282935ffdee29e9d51ddd53e2 +size 351445632 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q2_K.gguf b/Qwen2.5-0.5B-Distill-Fast.Q2_K.gguf new file mode 100644 index 0000000..e7707c1 --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7c79c6c0380eaeea7a74045ecd40bc8cc2a3f2ff359711957c8eeb9875a3ab +size 338607744 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q3_K_L.gguf b/Qwen2.5-0.5B-Distill-Fast.Q3_K_L.gguf new file mode 100644 index 0000000..61bc1cf --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78b44d96f443f2d857d6cc96b90419be2a1911199491901229b8a3415aad6ec1 +size 369358464 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q3_K_M.gguf b/Qwen2.5-0.5B-Distill-Fast.Q3_K_M.gguf new file mode 100644 index 0000000..fdc6e46 --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4372ab1f339db98ba63b56f9b08df35ed5cdb3f7fa921e226878757623f676 +size 355466880 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q3_K_S.gguf b/Qwen2.5-0.5B-Distill-Fast.Q3_K_S.gguf new file mode 100644 index 0000000..e4aadae --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3226a1f3bfaeae43a445c3be4ae73f2bfd769e57d7b9ca1a8ce79c9b1dc4f6e +size 338263680 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q4_K_M.gguf b/Qwen2.5-0.5B-Distill-Fast.Q4_K_M.gguf new file mode 100644 index 0000000..aa010e2 --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9dffffe50da681ebb0c0d2de98ec0dc10f096cbe6b56e18830464c7e5938cf0 +size 397808256 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q4_K_S.gguf b/Qwen2.5-0.5B-Distill-Fast.Q4_K_S.gguf new file mode 100644 index 0000000..7412f98 --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39071393f23a85f547a77c7d4630cd1d9aa7f0561d446b50a5d915a1da44e2c1 +size 385472128 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q5_K_M.gguf b/Qwen2.5-0.5B-Distill-Fast.Q5_K_M.gguf new file mode 100644 index 0000000..c91fdc5 --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a036bbcf031f08face255cba4e0710c537dfd207e43c34d9aa8df0a1cc9dd9ac +size 420086400 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q5_K_S.gguf b/Qwen2.5-0.5B-Distill-Fast.Q5_K_S.gguf new file mode 100644 index 0000000..708914f --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4216f2bfb0ac6d5c81bebbaa2c5d83b79ff74d562ae52b7306eb77a4f59a3f1c +size 412710528 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q6_K.gguf b/Qwen2.5-0.5B-Distill-Fast.Q6_K.gguf new file mode 100644 index 0000000..6c737e3 --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a10a355c2ab1e3fad33b52ecb9411edb8e6dbb27e95d3ee71c4ce791c410325 +size 505736832 diff --git a/Qwen2.5-0.5B-Distill-Fast.Q8_0.gguf b/Qwen2.5-0.5B-Distill-Fast.Q8_0.gguf new file mode 100644 index 0000000..8c6a509 --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e003088e1f9eac23c6901374d0b4a9b9dadba93ee948425c4374311a46d2b68 +size 531068544 diff --git a/Qwen2.5-0.5B-Distill-Fast.f16.gguf b/Qwen2.5-0.5B-Distill-Fast.f16.gguf new file mode 100644 index 0000000..0cc9cd1 --- /dev/null +++ b/Qwen2.5-0.5B-Distill-Fast.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17b70d4a0d556e48634b07e6ec37bb9710632c3198a9b07d409b1463ee27cd6 +size 994157184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f67405f --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: chinmaydk99/Qwen2.5-0.5B-Open-R1-Distill-Small +language: +- en +library_name: transformers +model_name: Qwen2.5-0.5B-Distill-Fast +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/chinmaydk99/Qwen2.5-0.5B-Open-R1-Distill-Small + + +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/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Distill-Fast-GGUF/resolve/main/Qwen2.5-0.5B-Distill-Fast.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. 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. + +