commit be55cf37ba9ede5b73775b1ee43d44dcf259cd81 Author: ModelHub XC Date: Mon Jun 1 20:44:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5cca7e1 --- /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 +Qwen3-LLMOPT-SFT-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-LLMOPT-SFT-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-LLMOPT-SFT-8B.IQ4_XS.gguf b/Qwen3-LLMOPT-SFT-8B.IQ4_XS.gguf new file mode 100644 index 0000000..d5e487b --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28c2e3234525d2f11011e290533ef200aaefb5bad09558f11fe8e73aee947a8f +size 4593293056 diff --git a/Qwen3-LLMOPT-SFT-8B.Q2_K.gguf b/Qwen3-LLMOPT-SFT-8B.Q2_K.gguf new file mode 100644 index 0000000..936544b --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1e9fcdd126a0d7720c93018551eece1330186fcfbcebcd90a6bb31b146c3dcc +size 3281729280 diff --git a/Qwen3-LLMOPT-SFT-8B.Q3_K_L.gguf b/Qwen3-LLMOPT-SFT-8B.Q3_K_L.gguf new file mode 100644 index 0000000..5295d34 --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28278ec2b6e999ad396456073b43d461850b4e6f2fd72e861f84533342c16f50 +size 4431390464 diff --git a/Qwen3-LLMOPT-SFT-8B.Q3_K_M.gguf b/Qwen3-LLMOPT-SFT-8B.Q3_K_M.gguf new file mode 100644 index 0000000..a41b9cb --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb5ed702dbba3a4eda446403c3d1bc7383145d64e6ca748037d8bbfa4d4084db +size 4124157696 diff --git a/Qwen3-LLMOPT-SFT-8B.Q3_K_S.gguf b/Qwen3-LLMOPT-SFT-8B.Q3_K_S.gguf new file mode 100644 index 0000000..ead802d --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea23cfc97fe82842dcffb3da76664a4e5bedc3920dc7ba2f736c35ea90eedd96 +size 3769607936 diff --git a/Qwen3-LLMOPT-SFT-8B.Q4_K_M.gguf b/Qwen3-LLMOPT-SFT-8B.Q4_K_M.gguf new file mode 100644 index 0000000..c08e56f --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9482b9e54f007f9c4beffc6c7e93ae855eb32e4a49f524d5a534d381c937b6a9 +size 5027780352 diff --git a/Qwen3-LLMOPT-SFT-8B.Q4_K_S.gguf b/Qwen3-LLMOPT-SFT-8B.Q4_K_S.gguf new file mode 100644 index 0000000..bebac5f --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8868a40cf24ed93284f546a876f0d5e40bac0cae96d01332f3917a2e75eb73b +size 4802008832 diff --git a/Qwen3-LLMOPT-SFT-8B.Q5_K_M.gguf b/Qwen3-LLMOPT-SFT-8B.Q5_K_M.gguf new file mode 100644 index 0000000..6f79f3f --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa04026836face6b2e3981772f5896b8cdf43e073ffc5cd4074f02ebf26ab03d +size 5851109120 diff --git a/Qwen3-LLMOPT-SFT-8B.Q5_K_S.gguf b/Qwen3-LLMOPT-SFT-8B.Q5_K_S.gguf new file mode 100644 index 0000000..99a70d9 --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7c24879f88f2d4743eb4311c1aae182f00a4bfc4ff20752a67446df1069f301 +size 5720758016 diff --git a/Qwen3-LLMOPT-SFT-8B.Q6_K.gguf b/Qwen3-LLMOPT-SFT-8B.Q6_K.gguf new file mode 100644 index 0000000..268dcca --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26cb770580698d673c7aa283e25c1c36c2d60b79ad58d2c3657a7184c75a53b0 +size 6725895936 diff --git a/Qwen3-LLMOPT-SFT-8B.Q8_0.gguf b/Qwen3-LLMOPT-SFT-8B.Q8_0.gguf new file mode 100644 index 0000000..d2baf42 --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555899fe899ead6e99fb13fcd7719bc025e9ab860798f70fb985cc132f4c8992 +size 8709515008 diff --git a/Qwen3-LLMOPT-SFT-8B.f16.gguf b/Qwen3-LLMOPT-SFT-8B.f16.gguf new file mode 100644 index 0000000..4af1515 --- /dev/null +++ b/Qwen3-LLMOPT-SFT-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3480cca81840d69bf6cb158326ca3956d2683944a11cb3c1bdd1e2ed87a51870 +size 16388040448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a466c90 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: zzhang1987/Qwen3-LLMOPT-SFT-8B +datasets: CardinalOperations/OR-Instruct-Data-3K +language: +- en +library_name: transformers +model_name: Qwen3-LLMOPT-SFT-8B +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/zzhang1987/Qwen3-LLMOPT-SFT-8B + + +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/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-LLMOPT-SFT-8B-GGUF/resolve/main/Qwen3-LLMOPT-SFT-8B.f16.gguf) | f16 | 16.5 | 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. + +