commit 803e5328909a9773b9c5ef3d9e37d4dadcc101d6 Author: ModelHub XC Date: Sun Jun 14 20:44:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6b12e12 --- /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-L52-Flat-tuned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5B-L52-Flat-tuned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5B-L52-Flat-tuned.IQ4_XS.gguf b/Qwen1.5B-L52-Flat-tuned.IQ4_XS.gguf new file mode 100644 index 0000000..29ee203 --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e22d7a9bbd566c4af8164a40a5f10a2afdcc357fb6491976d288ef51bdc8fce +size 1507223520 diff --git a/Qwen1.5B-L52-Flat-tuned.Q2_K.gguf b/Qwen1.5B-L52-Flat-tuned.Q2_K.gguf new file mode 100644 index 0000000..eed53d1 --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b55ed44b876a7470aac457ede6cb82a707ff20761862bfeaf101a93f48ee956d +size 1086814176 diff --git a/Qwen1.5B-L52-Flat-tuned.Q3_K_L.gguf b/Qwen1.5B-L52-Flat-tuned.Q3_K_L.gguf new file mode 100644 index 0000000..37593d3 --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52e9f9efec80d557444065c2c8855999a9ead70b5cd494658f37780f90119a5 +size 1465407456 diff --git a/Qwen1.5B-L52-Flat-tuned.Q3_K_M.gguf b/Qwen1.5B-L52-Flat-tuned.Q3_K_M.gguf new file mode 100644 index 0000000..e34db1c --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb363131272d6063b8f74f8da613376545d61d2f769c5153c2f4356c8ca5aa6 +size 1363318752 diff --git a/Qwen1.5B-L52-Flat-tuned.Q3_K_S.gguf b/Qwen1.5B-L52-Flat-tuned.Q3_K_S.gguf new file mode 100644 index 0000000..a0ed1b4 --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc23ec48159c09a6eebab2c910d1f5f28f5919dab40f4165af7bda04c3358a7 +size 1244002272 diff --git a/Qwen1.5B-L52-Flat-tuned.Q4_K_M.gguf b/Qwen1.5B-L52-Flat-tuned.Q4_K_M.gguf new file mode 100644 index 0000000..0b1a12f --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82cc28ec92531ed177c41be60e2fee62d8a79b9dff61677d1c589542929a9862 +size 1662052320 diff --git a/Qwen1.5B-L52-Flat-tuned.Q4_K_S.gguf b/Qwen1.5B-L52-Flat-tuned.Q4_K_S.gguf new file mode 100644 index 0000000..0f8c45f --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c411b3f68411d7c92aba22c55e9cf10bd64a758ffd7d345c07944135048ea3da +size 1577682912 diff --git a/Qwen1.5B-L52-Flat-tuned.Q5_K_M.gguf b/Qwen1.5B-L52-Flat-tuned.Q5_K_M.gguf new file mode 100644 index 0000000..44b225f --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:517ddfe769e811c08e63dc8d8b2e114962b706384eeb481c5533be59d0a1bbef +size 1920198624 diff --git a/Qwen1.5B-L52-Flat-tuned.Q5_K_S.gguf b/Qwen1.5B-L52-Flat-tuned.Q5_K_S.gguf new file mode 100644 index 0000000..31bc570 --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a377f081c396a6a23284dbf51b544acb344993e6dbe79eb55f00584120ec4734 +size 1871316960 diff --git a/Qwen1.5B-L52-Flat-tuned.Q6_K.gguf b/Qwen1.5B-L52-Flat-tuned.Q6_K.gguf new file mode 100644 index 0000000..4fb2f7f --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbbd6c0bbde09bed1e28452ce4c99ef835e07489b88382f1e95c6c946957d30d +size 2194479072 diff --git a/Qwen1.5B-L52-Flat-tuned.Q8_0.gguf b/Qwen1.5B-L52-Flat-tuned.Q8_0.gguf new file mode 100644 index 0000000..b47668a --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc5f471496890d2b8ee3cae9e8ce7fbf88e0365309ad74147cd21124baa2cf42 +size 2840294880 diff --git a/Qwen1.5B-L52-Flat-tuned.f16.gguf b/Qwen1.5B-L52-Flat-tuned.f16.gguf new file mode 100644 index 0000000..9fa065d --- /dev/null +++ b/Qwen1.5B-L52-Flat-tuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f86d7194a7660d3a97a07650fd198de63e2d0e6af0c2dbc309187b54858dadd +size 5340227040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bf9706f --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: ZMC2019/Qwen1.5B-L52-Flat-tuned +datasets: open-r1/OpenR1-Math-220k +language: +- en +library_name: transformers +model_name: Qwen1.5B-L52-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-L52-Flat-tuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen1.5B-L52-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-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q2_K.gguf) | Q2_K | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q3_K_S.gguf) | Q3_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q5_K_M.gguf) | Q5_K_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.Q8_0.gguf) | Q8_0 | 2.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5B-L52-Flat-tuned-GGUF/resolve/main/Qwen1.5B-L52-Flat-tuned.f16.gguf) | f16 | 5.4 | 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. + +