commit 3d37a015e91334decbc270643ddb3a4411d22fcd Author: ModelHub XC Date: Thu Jun 25 17:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2143280 --- /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_instruct_reasoning_finetune.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5_0.5b_instruct_reasoning_finetune.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cc1c7d6 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: minhtuan7akp/qwen2.5_0.5b_instruct_reasoning_finetune +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/minhtuan7akp/qwen2.5_0.5b_instruct_reasoning_finetune + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen2.5_0.5b_instruct_reasoning_finetune-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/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5_0.5b_instruct_reasoning_finetune-GGUF/resolve/main/qwen2.5_0.5b_instruct_reasoning_finetune.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. + + diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.IQ4_XS.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.IQ4_XS.gguf new file mode 100644 index 0000000..a790038 --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89b599b63c49e6877430580f4198dedd8545d4909f5d59b1398994b3e265f6fc +size 351445760 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q2_K.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q2_K.gguf new file mode 100644 index 0000000..6f05d2e --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:708e61b6092e311655a2a7bd4263ea1fbffeb64650b4dbfc750f747493bad6ce +size 338607872 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_L.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_L.gguf new file mode 100644 index 0000000..81f9a87 --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23d91df6b89047b8d04ea2b41241c3966e8b43acd274eefcc6d4a84f8f5bd12 +size 369358592 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_M.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_M.gguf new file mode 100644 index 0000000..2fb64ed --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b287495d2c2dd57170f1d58135dccc354212b10ae896ad5038342556d3a1088 +size 355467008 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_S.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_S.gguf new file mode 100644 index 0000000..2aa8e72 --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:658779c8bf14dcc6f1c5bfab65e77367688f7df2f7584bd310dd2ebabf5b39ac +size 338263808 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_M.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_M.gguf new file mode 100644 index 0000000..0010f70 --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0830893c9ad01a78c93bc1dbba4ef4234499142bf33e7e166363519de4e2e44b +size 397808384 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_S.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_S.gguf new file mode 100644 index 0000000..8f24a3c --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b17775a2c0339ac949b76cbc5a649cc4750376b5e425e1ba80b9369b44db1c5 +size 385472256 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_M.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_M.gguf new file mode 100644 index 0000000..f1d8f57 --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7227d4c99c4778be24af99f9723e0b98ad0a4fae11cfb9bbce939d844e12a5a9 +size 420086528 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_S.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_S.gguf new file mode 100644 index 0000000..f038116 --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952355e107ffab058c0a69c0d28564cb7be5dcb6f449b79c6a07f69898f21a7f +size 412710656 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q6_K.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q6_K.gguf new file mode 100644 index 0000000..af13056 --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8f20e0d43e714e14084a2ecf7bb588d08f28de8c47cd3e1537f138cec06964 +size 505736960 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.Q8_0.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.Q8_0.gguf new file mode 100644 index 0000000..8ea1bbe --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7274dd46c714ef1edb583f8d8d9fe9da8a2627a0f1fba1433a9e4cf40f8a76e +size 531068672 diff --git a/qwen2.5_0.5b_instruct_reasoning_finetune.f16.gguf b/qwen2.5_0.5b_instruct_reasoning_finetune.f16.gguf new file mode 100644 index 0000000..115a20c --- /dev/null +++ b/qwen2.5_0.5b_instruct_reasoning_finetune.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcefbcd9e7a4aa74cb8fa120dccfb57895f8f8fede3afdaa9d6b6c37833b5396 +size 994157312