commit b2207468af30b54831fa951133abffab39da2d32 Author: ModelHub XC Date: Tue Jul 21 09:41:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ffefbfe --- /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 +Qwen-2.5-7B-ConsistentChat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-ConsistentChat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-2.5-7B-ConsistentChat.IQ4_XS.gguf b/Qwen-2.5-7B-ConsistentChat.IQ4_XS.gguf new file mode 100644 index 0000000..2073fdc --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:876b78da08cb6ce020dd70da923565d39f622aaddda641614d9ed3ab9a0bb371 +size 4250298720 diff --git a/Qwen-2.5-7B-ConsistentChat.Q2_K.gguf b/Qwen-2.5-7B-ConsistentChat.Q2_K.gguf new file mode 100644 index 0000000..a9276ba --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f798c2c042d771ac8547f3cc9727d7c064aa19610e7454d5ad070f54c7f7413 +size 3015940448 diff --git a/Qwen-2.5-7B-ConsistentChat.Q3_K_L.gguf b/Qwen-2.5-7B-ConsistentChat.Q3_K_L.gguf new file mode 100644 index 0000000..2b20a31 --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed876d3f1190503ce4f547f4b70baf9837f3a81d9f74247be17cb57b2226e0f1 +size 4088459616 diff --git a/Qwen-2.5-7B-ConsistentChat.Q3_K_M.gguf b/Qwen-2.5-7B-ConsistentChat.Q3_K_M.gguf new file mode 100644 index 0000000..3920a1b --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4afe94ca887aa15ef4645a680da3beae894b14f3dfc7ec84369a407728df8fe3 +size 3808391520 diff --git a/Qwen-2.5-7B-ConsistentChat.Q3_K_S.gguf b/Qwen-2.5-7B-ConsistentChat.Q3_K_S.gguf new file mode 100644 index 0000000..219a059 --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c558314c10671f25c0ea6d29a0a87d5f24fb29907206d3b244da158a335a1b6 +size 3492368736 diff --git a/Qwen-2.5-7B-ConsistentChat.Q4_K_M.gguf b/Qwen-2.5-7B-ConsistentChat.Q4_K_M.gguf new file mode 100644 index 0000000..f664594 --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9c2a7a4ab05bcf87213ec5868030e29d2c8c73ef6a8022b88655687ae5cb89 +size 4683073888 diff --git a/Qwen-2.5-7B-ConsistentChat.Q4_K_S.gguf b/Qwen-2.5-7B-ConsistentChat.Q4_K_S.gguf new file mode 100644 index 0000000..b8e1631 --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b3e727c70e8698a952ea37485219dc5e7084557f1c3cf50821d068d1892bbbe +size 4457769312 diff --git a/Qwen-2.5-7B-ConsistentChat.Q5_K_M.gguf b/Qwen-2.5-7B-ConsistentChat.Q5_K_M.gguf new file mode 100644 index 0000000..25c564f --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5dc16eb8ab98a4f6bbce047c4a30592875a727dfcf1316390a6fa8098342a31 +size 5444831584 diff --git a/Qwen-2.5-7B-ConsistentChat.Q5_K_S.gguf b/Qwen-2.5-7B-ConsistentChat.Q5_K_S.gguf new file mode 100644 index 0000000..442c628 --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5fd4f594726cfc30dd2604150a97084845346fc01b3765ce43799e914d1fb1 +size 5315176800 diff --git a/Qwen-2.5-7B-ConsistentChat.Q6_K.gguf b/Qwen-2.5-7B-ConsistentChat.Q6_K.gguf new file mode 100644 index 0000000..146d812 --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a75ace35da5c8dfdd80bf9507ebb72db23e1b5b4c038aec5d9884579b920c6 +size 6254199136 diff --git a/Qwen-2.5-7B-ConsistentChat.Q8_0.gguf b/Qwen-2.5-7B-ConsistentChat.Q8_0.gguf new file mode 100644 index 0000000..450a09a --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36d9096f81e89b70fce513c535620e74f68ff36266207484b5a21558b064519a +size 8098525536 diff --git a/Qwen-2.5-7B-ConsistentChat.f16.gguf b/Qwen-2.5-7B-ConsistentChat.f16.gguf new file mode 100644 index 0000000..19a6bbb --- /dev/null +++ b/Qwen-2.5-7B-ConsistentChat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4ab1ef09ae82dcaedca940ab9662ee9a123115502324a1e30999f0ad01078d +size 15237853536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5a23909 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: jiawei-ucas/Qwen-2.5-7B-ConsistentChat +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- chat +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jiawei-ucas/Qwen-2.5-7B-ConsistentChat + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-2.5-7B-ConsistentChat-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/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-ConsistentChat-GGUF/resolve/main/Qwen-2.5-7B-ConsistentChat.f16.gguf) | f16 | 15.3 | 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. + +