commit e6b46296cd6884bb6b8b3fb560905e584919e7e5 Author: ModelHub XC Date: Sat Jul 18 06:07:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7f8a457 --- /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 +Qwen2.5-1.5B-Instruct-CoT-Reflection.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-CoT-Reflection.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.IQ4_XS.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.IQ4_XS.gguf new file mode 100644 index 0000000..634732d --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:273df5d55e1b178adfaab4cc6a2f803611c89d7f437f5b68747c2272d59f1864 +size 902183904 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q2_K.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q2_K.gguf new file mode 100644 index 0000000..9a14786 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c175aa13cf32aef3a8852250396e0075db1ac2a6bceba82242e60636a4e16f +size 676305888 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_L.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_L.gguf new file mode 100644 index 0000000..7937092 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b25a516e1d20738ca264ea4192c540f12d10351eb65516cc4cfbfaeebdba5c03 +size 880163808 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_M.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_M.gguf new file mode 100644 index 0000000..0a5427f --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55964fca80cc1e45380ab9f9df128c0bb486f41731f1c9971c5afe2f6743c040 +size 824179680 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_S.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_S.gguf new file mode 100644 index 0000000..b2fb45f --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c980c604656cbee4dc79bd6f8a2ca9146b18e0ce19970d4ef9ea2981632fca3 +size 760945632 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_M.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_M.gguf new file mode 100644 index 0000000..c34da88 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a129d2ca8b6454b34b028b4112e40e2dd4ed42e04549c9453bdd02d5724730b +size 986049504 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_S.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_S.gguf new file mode 100644 index 0000000..43bbdc6 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4daf99c9697dd0b1bfd51fc99ff9a362c2c47faee4c748afdf05e4fe3fd35a45 +size 940313568 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_M.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_M.gguf new file mode 100644 index 0000000..6ead530 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f9a23883102fe9fd6a1a808b89e90484b2823e9083adacfedeb6f0bb887965c +size 1125051360 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_S.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_S.gguf new file mode 100644 index 0000000..b01a146 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ac0de233c704a68eaf413a9fd189eb79f2c1d8d7420274afbd6d2df704e97b +size 1098730464 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q6_K.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q6_K.gguf new file mode 100644 index 0000000..803480d --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8731f67f2e7adc60edc96d80862080abe7f01814cee9791555494456bdfe507 +size 1272740832 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q8_0.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q8_0.gguf new file mode 100644 index 0000000..9eb783f --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2855389b541b852577431314b4fcfd081b3d32cdfb02262e7ba6763d552354d +size 1646574048 diff --git a/Qwen2.5-1.5B-Instruct-CoT-Reflection.f16.gguf b/Qwen2.5-1.5B-Instruct-CoT-Reflection.f16.gguf new file mode 100644 index 0000000..dcf5c8a --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-CoT-Reflection.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0f0057dc787c2bf907de30f34d4379d4bca630f7e5520954fb778ed14edeb36 +size 3093670368 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5d7f47e --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: mosama/Qwen2.5-1.5B-Instruct-CoT-Reflection +datasets: +- argilla/magpie-ultra-v1.0 +- mosama/CoT-Reflection +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- reflection +- cot +- qwen +- instruct +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/mosama/Qwen2.5-1.5B-Instruct-CoT-Reflection + + +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/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-CoT-Reflection-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-CoT-Reflection.f16.gguf) | f16 | 3.2 | 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. + +