commit 2028f0f94df7ff506f9e377b01584defe32fc6fa Author: ModelHub XC Date: Fri May 1 03:41:49 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen3-lora-warm-4o-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7df11e2 --- /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-lora-warm-4o.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-lora-warm-4o.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..496683d --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: maduprey/qwen3-lora-warm-4o +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/maduprey/qwen3-lora-warm-4o + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen3-lora-warm-4o-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/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-lora-warm-4o-GGUF/resolve/main/qwen3-lora-warm-4o.f16.gguf) | f16 | 8.2 | 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. + + diff --git a/qwen3-lora-warm-4o.IQ4_XS.gguf b/qwen3-lora-warm-4o.IQ4_XS.gguf new file mode 100644 index 0000000..2596574 --- /dev/null +++ b/qwen3-lora-warm-4o.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff3fbeb4b28aefb01316392e2516c99d2256521a5a6cdbf717d03a260c7e89e +size 2286316640 diff --git a/qwen3-lora-warm-4o.Q2_K.gguf b/qwen3-lora-warm-4o.Q2_K.gguf new file mode 100644 index 0000000..bafaabb --- /dev/null +++ b/qwen3-lora-warm-4o.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e97a460a989abb1d4c7ed6a8539257632a41643cab8de438cba35b4ab730b6 +size 1669500000 diff --git a/qwen3-lora-warm-4o.Q3_K_L.gguf b/qwen3-lora-warm-4o.Q3_K_L.gguf new file mode 100644 index 0000000..b9ac290 --- /dev/null +++ b/qwen3-lora-warm-4o.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7302928761006e1c77fafd2b5cfeb7eaa641065be041a52a2ed4e1059e75cec2 +size 2239786080 diff --git a/qwen3-lora-warm-4o.Q3_K_M.gguf b/qwen3-lora-warm-4o.Q3_K_M.gguf new file mode 100644 index 0000000..0b3acef --- /dev/null +++ b/qwen3-lora-warm-4o.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef8001b4b35a1f3fc218e4480f8d2125eae05fa5b7b4b03a1270acbd0ebec05 +size 2075618400 diff --git a/qwen3-lora-warm-4o.Q3_K_S.gguf b/qwen3-lora-warm-4o.Q3_K_S.gguf new file mode 100644 index 0000000..86ed817 --- /dev/null +++ b/qwen3-lora-warm-4o.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73dce5fb95be5566e0e54537e2e2a333da6763c110b792fc8fed5ba5946b192 +size 1886997600 diff --git a/qwen3-lora-warm-4o.Q4_K_M.gguf b/qwen3-lora-warm-4o.Q4_K_M.gguf new file mode 100644 index 0000000..eca189d --- /dev/null +++ b/qwen3-lora-warm-4o.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d0cdc97f931c55fc48882ce07f3113768db9709a4f1623dd005abeb90e988b +size 2497281120 diff --git a/qwen3-lora-warm-4o.Q4_K_S.gguf b/qwen3-lora-warm-4o.Q4_K_S.gguf new file mode 100644 index 0000000..d01ab5f --- /dev/null +++ b/qwen3-lora-warm-4o.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d66256fce34f20c402ac248ad79fce424333c0c2e94ffe1fec395b5b6fa982 +size 2383309920 diff --git a/qwen3-lora-warm-4o.Q5_K_M.gguf b/qwen3-lora-warm-4o.Q5_K_M.gguf new file mode 100644 index 0000000..77d2c30 --- /dev/null +++ b/qwen3-lora-warm-4o.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13ade0ac7c7b8f97897cff318477af0c337bebed836a0e343b513d1083a75b81 +size 2889514080 diff --git a/qwen3-lora-warm-4o.Q5_K_S.gguf b/qwen3-lora-warm-4o.Q5_K_S.gguf new file mode 100644 index 0000000..c9e766a --- /dev/null +++ b/qwen3-lora-warm-4o.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c4aad5f7eb8f68707fcc209b6ead8338db09b7e6fbe07676b030239f1b8e0fb +size 2823711840 diff --git a/qwen3-lora-warm-4o.Q6_K.gguf b/qwen3-lora-warm-4o.Q6_K.gguf new file mode 100644 index 0000000..bda7862 --- /dev/null +++ b/qwen3-lora-warm-4o.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12adf5b64f7830858136336cb9bc255a4a42bb0885b30e0e66dbc700255baefe +size 3306261600 diff --git a/qwen3-lora-warm-4o.Q8_0.gguf b/qwen3-lora-warm-4o.Q8_0.gguf new file mode 100644 index 0000000..8f9f137 --- /dev/null +++ b/qwen3-lora-warm-4o.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582a41fb9449fabd24acee392c74054b0f4095b60e104e5e128c613e448ef45e +size 4280405600 diff --git a/qwen3-lora-warm-4o.f16.gguf b/qwen3-lora-warm-4o.f16.gguf new file mode 100644 index 0000000..c6174c0 --- /dev/null +++ b/qwen3-lora-warm-4o.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cce139e24646f42ac393fe63751136c09735be0760e1cadbd77e44445a106cf1 +size 8051285600