commit ef1647ae63aa5613b953dce2f1ab540bc53e79bc Author: ModelHub XC Date: Sun Jun 14 20:28:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5693524 --- /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-L36-Flat-tuned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L36-Flat-tuned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5B-L36-Flat-tuned.IQ4_XS.gguf b/Qwen1.5B-L36-Flat-tuned.IQ4_XS.gguf new file mode 100644 index 0000000..7b6de9e --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:251c40b8bb4fb86570ab78c4989f118eeb3912b96da8947d70e0023e9b7c2eaf +size 1103863008 diff --git a/Qwen1.5B-L36-Flat-tuned.Q2_K.gguf b/Qwen1.5B-L36-Flat-tuned.Q2_K.gguf new file mode 100644 index 0000000..bd4fad6 --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e20a29fc73604dc6f2d1bd9d64529cfe6859d8debe8fc75cca231ce3cf5139 +size 813141216 diff --git a/Qwen1.5B-L36-Flat-tuned.Q3_K_L.gguf b/Qwen1.5B-L36-Flat-tuned.Q3_K_L.gguf new file mode 100644 index 0000000..d21ca2f --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beef7edf6d04082d5081f7116453d221fbfe89b8e72baa174c8bca5fa94e003c +size 1075244256 diff --git a/Qwen1.5B-L36-Flat-tuned.Q3_K_M.gguf b/Qwen1.5B-L36-Flat-tuned.Q3_K_M.gguf new file mode 100644 index 0000000..8ea317c --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db93afe551c80aefe1253b0cf29cf1d3255f6d65e6706433946e68b7b17441ee +size 1004465376 diff --git a/Qwen1.5B-L36-Flat-tuned.Q3_K_S.gguf b/Qwen1.5B-L36-Flat-tuned.Q3_K_S.gguf new file mode 100644 index 0000000..e619f9c --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:046f8097304e67dea955d75a92cfb2a2bf056c8d16f66a393e9900f40f0e312c +size 921963744 diff --git a/Qwen1.5B-L36-Flat-tuned.Q4_K_M.gguf b/Qwen1.5B-L36-Flat-tuned.Q4_K_M.gguf new file mode 100644 index 0000000..9991712 --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:517f60019c434ec63be37a5e9d8aaa5c48430b733bfaf9e65d3c540a4b0ce637 +size 1211383008 diff --git a/Qwen1.5B-L36-Flat-tuned.Q4_K_S.gguf b/Qwen1.5B-L36-Flat-tuned.Q4_K_S.gguf new file mode 100644 index 0000000..a1e29af --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6721db99963e084e5430649138e530b79818f6496a04c4d5c169755bf1b7062 +size 1152769248 diff --git a/Qwen1.5B-L36-Flat-tuned.Q5_K_M.gguf b/Qwen1.5B-L36-Flat-tuned.Q5_K_M.gguf new file mode 100644 index 0000000..da168bc --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36cc34280a41cac066b069a39f89ca1bebf208a8902d46d049320fc7f3058ab8 +size 1390099680 diff --git a/Qwen1.5B-L36-Flat-tuned.Q5_K_S.gguf b/Qwen1.5B-L36-Flat-tuned.Q5_K_S.gguf new file mode 100644 index 0000000..91f6f2f --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e243daac46635df72bb2a8621e995337f9640c3d79e5ea7d1d2c877ecf972d93 +size 1356258528 diff --git a/Qwen1.5B-L36-Flat-tuned.Q6_K.gguf b/Qwen1.5B-L36-Flat-tuned.Q6_K.gguf new file mode 100644 index 0000000..e3a89ec --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e94ae464d1538f84046559fb781c5e9fd9cf2edf238c1df83182d4ce7375f50 +size 1579986144 diff --git a/Qwen1.5B-L36-Flat-tuned.Q8_0.gguf b/Qwen1.5B-L36-Flat-tuned.Q8_0.gguf new file mode 100644 index 0000000..c63479e --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b06514e78026cb5a63abb7a3b3d6e3260ad22b70faf6c85ca7fcdf96691310 +size 2044480224 diff --git a/Qwen1.5B-L36-Flat-tuned.f16.gguf b/Qwen1.5B-L36-Flat-tuned.f16.gguf new file mode 100644 index 0000000..cdfe3d8 --- /dev/null +++ b/Qwen1.5B-L36-Flat-tuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fec1bfa14678b8c2b0aef22583b1ae543bd463558fbd4c78b158c49ae450cb3 +size 3842521824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c028da0 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: ZMC2019/Qwen1.5B-L36-Flat-tuned +datasets: open-r1/OpenR1-Math-220k +language: +- en +library_name: transformers +model_name: Qwen1.5B-L36-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-L36-Flat-tuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen1.5B-L36-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-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.IQ4_XS.gguf) | IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q5_K_S.gguf) | Q5_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.Q8_0.gguf) | Q8_0 | 2.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L36-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L36-Flat-tuned.f16.gguf) | f16 | 3.9 | 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. + +