commit 7209d51de0556d70e51c691f89b3c211ac7342f2 Author: ModelHub XC Date: Fri Jul 17 12:25:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fe83c5c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen2.5-3B-RuoZhiBa-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-RuoZhiBa-Instruct.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.IQ4_XS.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..ef20914 --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d120321650661789ab962ca16be52eee544e003d9b86eb9d28fe0c416a96c62 +size 1753185728 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q2_K.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q2_K.gguf new file mode 100644 index 0000000..fef9a97 --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f44deab115b3982bfefc34c78d6d1269944bbc6a7841732d7a387d474866b2f8 +size 1274756544 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_L.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..39f3d76 --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:256bcaab6086a8a3a1451e472168b0a34876e0253b91c2252a0ae3a7f09a407f +size 1707392448 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_M.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..d21eff9 --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f3f2707d7e78a104bbd9df55e1811f65958a7a64222fdc6c2ac11b44cb8abb +size 1590476224 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_S.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..c8b6778 --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e555534286abeada3c770319cf9b1d614640406601b61ec9f68c73d20fa4a36d +size 1454357952 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_0_4_4.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_0_4_4.gguf new file mode 100644 index 0000000..fcc41da --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e1c2f27f093b6fb97519a32a78fc05c11ea2e5bb376923ea62002560530f742 +size 1822850496 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_M.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..75025fc --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dff8132ff58fcd2dbf7e4c4ba539281193943e435b56a5475b66eb5f05a41f0b +size 1929903552 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_S.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c3e9f7c --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79de4c1b2c763563386e1183f9c6d84ae567e063adea3111f44c357365924339 +size 1834384832 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_M.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..7bbb32d --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03447cccfa57cbc2b041168411d262417e33dd8bc6524cef836eb77c0286fb1c +size 2224815552 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_S.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..db6c56e --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc4ce4133f0ef1ea9cb8f2bee2c12872dd80e374742b5206719359bf5db4ada3 +size 2169667008 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q6_K.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q6_K.gguf new file mode 100644 index 0000000..2d6880f --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7abf1ea980170ea32eec765923d793868e218432ee78147fc047b608b37dcebb +size 2538159552 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.Q8_0.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.Q8_0.gguf new file mode 100644 index 0000000..6258a52 --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249316b86547447af6ee8976545239651dcea4b696a3d4ef07c3d9dd046dc95e +size 3285476800 diff --git a/Qwen2.5-3B-RuoZhiBa-Instruct.f16.gguf b/Qwen2.5-3B-RuoZhiBa-Instruct.f16.gguf new file mode 100644 index 0000000..942ccdd --- /dev/null +++ b/Qwen2.5-3B-RuoZhiBa-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836dd98c75d9ef62e9737b9db50977e1abcc15a73b6ed7bbbcb41817de777dfd +size 6178317760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..555b101 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: deeptoken/Qwen2.5-3B-RuoZhiBa-Instruct +datasets: +- hfl/ruozhiba_gpt4 +language: +- en +- zh +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/deeptoken/Qwen2.5-3B-RuoZhiBa-Instruct + + +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/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-RuoZhiBa-Instruct-GGUF/resolve/main/Qwen2.5-3B-RuoZhiBa-Instruct.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. + +