commit 5b7d130989e930a37700873b9ef252e3bad570db Author: ModelHub XC Date: Sat Jul 18 06:55:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen2.5-with-lora-think-3b-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1eac0b1 --- /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 +qwen2.5-with-lora-think-3b-it.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-with-lora-think-3b-it.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..640313d --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ehristoforu/qwen2.5-with-lora-think-3b-it +language: +- en +library_name: transformers +license: other +license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE +license_name: qwen-research +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/ehristoforu/qwen2.5-with-lora-think-3b-it + + +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/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen2.5-with-lora-think-3b-it-GGUF/resolve/main/qwen2.5-with-lora-think-3b-it.f16.gguf) | f16 | 6.3 | 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/qwen2.5-with-lora-think-3b-it.IQ4_XS.gguf b/qwen2.5-with-lora-think-3b-it.IQ4_XS.gguf new file mode 100644 index 0000000..35a2086 --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01744cdd9c461d715f27c98549cb4754f866764eae0be2af5137cf699d93480 +size 1753185696 diff --git a/qwen2.5-with-lora-think-3b-it.Q2_K.gguf b/qwen2.5-with-lora-think-3b-it.Q2_K.gguf new file mode 100644 index 0000000..d15bd1e --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b2afe00d5d54c070a9e69f4a8b1806821e1dcaa0a4e5480bd700b523b55da2a +size 1274756512 diff --git a/qwen2.5-with-lora-think-3b-it.Q3_K_L.gguf b/qwen2.5-with-lora-think-3b-it.Q3_K_L.gguf new file mode 100644 index 0000000..7d4012c --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bcda06b58cd0f685cbf3576c5997724068839238cd171af23c40fb1302099a5 +size 1707392416 diff --git a/qwen2.5-with-lora-think-3b-it.Q3_K_M.gguf b/qwen2.5-with-lora-think-3b-it.Q3_K_M.gguf new file mode 100644 index 0000000..802f680 --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d50df88f0c5d23fd98ac6c43fb1b9eb7432d1bacca32208da718f633e03951 +size 1590476192 diff --git a/qwen2.5-with-lora-think-3b-it.Q3_K_S.gguf b/qwen2.5-with-lora-think-3b-it.Q3_K_S.gguf new file mode 100644 index 0000000..c65a6a4 --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252111a75d79603e3505ec9974ef29308c0abbb3354966228128de91760138c7 +size 1454357920 diff --git a/qwen2.5-with-lora-think-3b-it.Q4_K_M.gguf b/qwen2.5-with-lora-think-3b-it.Q4_K_M.gguf new file mode 100644 index 0000000..d1d4d5c --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ffc853895ca7d31eb8c5db2d98d4d8538fd833789fbed519ef52af78bc84b7 +size 1929903520 diff --git a/qwen2.5-with-lora-think-3b-it.Q4_K_S.gguf b/qwen2.5-with-lora-think-3b-it.Q4_K_S.gguf new file mode 100644 index 0000000..1a29d38 --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1370b3228fbbf405bc5e5ca02d152739c9ec9e748d91d82f2437ef64c882e91 +size 1834384800 diff --git a/qwen2.5-with-lora-think-3b-it.Q5_K_M.gguf b/qwen2.5-with-lora-think-3b-it.Q5_K_M.gguf new file mode 100644 index 0000000..32455b3 --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec3f57af1a0948f6da3ac2082e2ba7a3a6674765687a2040023f169465fd488 +size 2224815520 diff --git a/qwen2.5-with-lora-think-3b-it.Q5_K_S.gguf b/qwen2.5-with-lora-think-3b-it.Q5_K_S.gguf new file mode 100644 index 0000000..27c305a --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edea649322914f547ab38f551cbcfbdc1745d1f0fb761b8b206d9349b3dd53c0 +size 2169666976 diff --git a/qwen2.5-with-lora-think-3b-it.Q6_K.gguf b/qwen2.5-with-lora-think-3b-it.Q6_K.gguf new file mode 100644 index 0000000..266aef3 --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58930ac89ecac55e18fd6331933751c5324ca47d77bc96259ab32307c73fc236 +size 2538159520 diff --git a/qwen2.5-with-lora-think-3b-it.Q8_0.gguf b/qwen2.5-with-lora-think-3b-it.Q8_0.gguf new file mode 100644 index 0000000..1147fa6 --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac4408da257073bcc00b96d40585649bea9286f3a6719a0209fdbdd9c396c4e8 +size 3285476768 diff --git a/qwen2.5-with-lora-think-3b-it.f16.gguf b/qwen2.5-with-lora-think-3b-it.f16.gguf new file mode 100644 index 0000000..afc3363 --- /dev/null +++ b/qwen2.5-with-lora-think-3b-it.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bfd70805b8fe0925360fc9104ae7f5f2850ad31a071e65d2ff5d37626c27799 +size 6178317728