commit 0075d8cefc1a986891647b7937b84528638a070f Author: ModelHub XC Date: Sun Jun 14 20:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53e8ea8 --- /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 +Qwen1.5B-L28-Flat-tuned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L28-Flat-tuned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5B-L28-Flat-tuned.IQ4_XS.gguf b/Qwen1.5B-L28-Flat-tuned.IQ4_XS.gguf new file mode 100644 index 0000000..3de9647 --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a351773ae452ce2d1f9d26cd2b5d2f4921a8d5b191bb6e07d1582cdc239efb37 +size 902182880 diff --git a/Qwen1.5B-L28-Flat-tuned.Q2_K.gguf b/Qwen1.5B-L28-Flat-tuned.Q2_K.gguf new file mode 100644 index 0000000..212bfc2 --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f64d51cf5550a1034ddad7e988a959ea867c02f460111480f5b525f54388cee3 +size 676304864 diff --git a/Qwen1.5B-L28-Flat-tuned.Q3_K_L.gguf b/Qwen1.5B-L28-Flat-tuned.Q3_K_L.gguf new file mode 100644 index 0000000..9a3dd17 --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0adb0328973a7a797bdf5057d491e7581c5a5dc39eb5b2c3913f2dbac9de82d5 +size 880162784 diff --git a/Qwen1.5B-L28-Flat-tuned.Q3_K_M.gguf b/Qwen1.5B-L28-Flat-tuned.Q3_K_M.gguf new file mode 100644 index 0000000..6bc8bee --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2c628e9a58029621476a324779c6fc1a3ad7e3d93c648e8ee696cb8396c4b8 +size 824178656 diff --git a/Qwen1.5B-L28-Flat-tuned.Q3_K_S.gguf b/Qwen1.5B-L28-Flat-tuned.Q3_K_S.gguf new file mode 100644 index 0000000..f884409 --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0b4248e4a6dece016b93d06697e742881589e2e1c1ceb4644a232c201420f36 +size 760944608 diff --git a/Qwen1.5B-L28-Flat-tuned.Q4_K_M.gguf b/Qwen1.5B-L28-Flat-tuned.Q4_K_M.gguf new file mode 100644 index 0000000..197c244 --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:894e7ca3f54a042b24cd29f9ed50876b7cc3d442225655feb06024109a362b0c +size 986048480 diff --git a/Qwen1.5B-L28-Flat-tuned.Q4_K_S.gguf b/Qwen1.5B-L28-Flat-tuned.Q4_K_S.gguf new file mode 100644 index 0000000..5ed343e --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16ff2ad7af3092e2e03260a6cadcd512368882b5c8f05cb2ddde300e9333cc8b +size 940312544 diff --git a/Qwen1.5B-L28-Flat-tuned.Q5_K_M.gguf b/Qwen1.5B-L28-Flat-tuned.Q5_K_M.gguf new file mode 100644 index 0000000..4ea82af --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:448d7913f0407829a0d057c9408fb015db0a2cf5ede188fa9ed6218f5d36f38a +size 1125050336 diff --git a/Qwen1.5B-L28-Flat-tuned.Q5_K_S.gguf b/Qwen1.5B-L28-Flat-tuned.Q5_K_S.gguf new file mode 100644 index 0000000..26c0e99 --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48802ef9220793363e925c9355b93a1367045bc51fd67041a33af38f27b7470 +size 1098729440 diff --git a/Qwen1.5B-L28-Flat-tuned.Q6_K.gguf b/Qwen1.5B-L28-Flat-tuned.Q6_K.gguf new file mode 100644 index 0000000..e1b2710 --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d2d6aee9c45683161d52f6bdd2b12ba4b9b45d05606a23560fbde2f44dff3d2 +size 1272739808 diff --git a/Qwen1.5B-L28-Flat-tuned.Q8_0.gguf b/Qwen1.5B-L28-Flat-tuned.Q8_0.gguf new file mode 100644 index 0000000..712911e --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26533a89f8d83262b237490ffa960abe3ab1682900b31508f74a7d987b0231f +size 1646573024 diff --git a/Qwen1.5B-L28-Flat-tuned.f16.gguf b/Qwen1.5B-L28-Flat-tuned.f16.gguf new file mode 100644 index 0000000..2bbf4a9 --- /dev/null +++ b/Qwen1.5B-L28-Flat-tuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b415a97463d4e40e73fa6f2e71091ffde9bffd677cde0fdf604b96efe33e71ea +size 3093669344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..56e3452 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: ZMC2019/Qwen1.5B-L28-Flat-tuned +datasets: open-r1/OpenR1-Math-220k +language: +- en +library_name: transformers +model_name: Qwen1.5B-L28-Flat-tuned +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/ZMC2019/Qwen1.5B-L28-Flat-tuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen1.5B-L28-Flat-tuned-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/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L28-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L28-Flat-tuned.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. + +