commit 82e384a763308aeccc3798747f0347c33397468b Author: ModelHub XC Date: Tue Jul 21 11:56:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-7B-sft-ultrachat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9a0a5bc --- /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 +Qwen2-7B-sft-ultrachat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-7B-sft-ultrachat.IQ4_XS.gguf b/Qwen2-7B-sft-ultrachat.IQ4_XS.gguf new file mode 100644 index 0000000..1831556 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3fa2e74d7353057ddeddd5b8f54aff4f0a3bc40242d9e251bf51a1e8acc6ce2 +size 4250296928 diff --git a/Qwen2-7B-sft-ultrachat.Q2_K.gguf b/Qwen2-7B-sft-ultrachat.Q2_K.gguf new file mode 100644 index 0000000..7657537 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f3136ea181f1fc679e5165c7dd753d63c69135f4223f93f7c1d10c3ffe2949 +size 3015938656 diff --git a/Qwen2-7B-sft-ultrachat.Q3_K_L.gguf b/Qwen2-7B-sft-ultrachat.Q3_K_L.gguf new file mode 100644 index 0000000..143a6b3 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:531ed3be1c12e8eebb47aef0efe19e977a7ec90b14e72960f139e901bd2915cb +size 4088457824 diff --git a/Qwen2-7B-sft-ultrachat.Q3_K_M.gguf b/Qwen2-7B-sft-ultrachat.Q3_K_M.gguf new file mode 100644 index 0000000..f8b0533 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eb8d4172613dc6cba3a61393f3e7fed710294ac0f7a5dd6af77b9a4f36a2012 +size 3808389728 diff --git a/Qwen2-7B-sft-ultrachat.Q3_K_S.gguf b/Qwen2-7B-sft-ultrachat.Q3_K_S.gguf new file mode 100644 index 0000000..071e71e --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07c3e9f060bb4dd18c663d469617c5ef559dfbb9afd7c199b2c095fe4f9ed179 +size 3492366944 diff --git a/Qwen2-7B-sft-ultrachat.Q4_K_M.gguf b/Qwen2-7B-sft-ultrachat.Q4_K_M.gguf new file mode 100644 index 0000000..2428646 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f68aa9fdb5ebc868bba34fe754efdccde1e2cf87d5b916bef342898a672054 +size 4683072096 diff --git a/Qwen2-7B-sft-ultrachat.Q4_K_S.gguf b/Qwen2-7B-sft-ultrachat.Q4_K_S.gguf new file mode 100644 index 0000000..e9c8d0d --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb2abc359b77271b0b47e9fa25cff4773484233adc4e3856b65d8907a7237b9 +size 4457767520 diff --git a/Qwen2-7B-sft-ultrachat.Q5_K_M.gguf b/Qwen2-7B-sft-ultrachat.Q5_K_M.gguf new file mode 100644 index 0000000..933c67d --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47a0229dfef37325ebec11943230a590663aa40aacb225ce83695bb172fe6f50 +size 5444829792 diff --git a/Qwen2-7B-sft-ultrachat.Q5_K_S.gguf b/Qwen2-7B-sft-ultrachat.Q5_K_S.gguf new file mode 100644 index 0000000..a27005d --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ed53c3dad08b1bebed6db21dcd97d962a7aa074db1fb9ad3a8b3d1a0fb83d3 +size 5315175008 diff --git a/Qwen2-7B-sft-ultrachat.Q6_K.gguf b/Qwen2-7B-sft-ultrachat.Q6_K.gguf new file mode 100644 index 0000000..8ce9e34 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc819a3893f270bcba0a7150bba2fcf437c1b3e3a981df773de4bb8ea52b708 +size 6254197344 diff --git a/Qwen2-7B-sft-ultrachat.Q8_0.gguf b/Qwen2-7B-sft-ultrachat.Q8_0.gguf new file mode 100644 index 0000000..302beaf --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e91f3fc30e6fb015558981a6ac2605bcd161f667c978234b47d843f384c5fb +size 8098523744 diff --git a/Qwen2-7B-sft-ultrachat.f16.gguf b/Qwen2-7B-sft-ultrachat.f16.gguf new file mode 100644 index 0000000..18d24f3 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9cbb3f2831a12b3ccc6666080d3531ffc2915e87a5dc9cc6a39c6ca5830e5b8 +size 15237851744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c9e4fd3 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/Qwen2-7B-sft-ultrachat +language: +- en +library_name: transformers +model_name: Qwen2-7B-sft-ultrachat +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2-7B-sft-ultrachat + + +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/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-GGUF/resolve/main/Qwen2-7B-sft-ultrachat.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. + +