commit a867dd7cf73923c226453b9914f8323df506248e Author: ModelHub XC Date: Tue Jul 21 03:01:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ff06b7 --- /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-safeRLHF.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-sft-ultrachat-safeRLHF.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.IQ4_XS.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.IQ4_XS.gguf new file mode 100644 index 0000000..f98bcfe --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05d59b61378aece4bcaca47d2347ca734a7d0ff0f7508815c8731da1a5e59a11 +size 4250296992 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q2_K.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q2_K.gguf new file mode 100644 index 0000000..f071e94 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7e1d95f705883a50c654dfefd793ff9c5edc5ab05e0fa1337c4e5fef54a3d9 +size 3015938720 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_L.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_L.gguf new file mode 100644 index 0000000..97aa8d5 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4213a4319387c53d48333e7c4b1170f0179f49da4c35c736da9bf725d5bdc1d +size 4088457888 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_M.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_M.gguf new file mode 100644 index 0000000..b7e69e3 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b81af19571bbecab5cd31739ca18b76fca9aa9ad5918357853531ddf062f28db +size 3808389792 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_S.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_S.gguf new file mode 100644 index 0000000..0130a41 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f578ddbc08d4c1b73976da0327428b063a00b92ba24763cc843b6a9bd312e128 +size 3492367008 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q4_K_M.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q4_K_M.gguf new file mode 100644 index 0000000..5d39075 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c449803aad1c79934bd734c399f6225b66b41e059dc7abea0c83124784beb0d5 +size 4683072160 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q4_K_S.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q4_K_S.gguf new file mode 100644 index 0000000..045e622 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:798c89cdccda6f8eed910e72fa2dca356a7a3a4551241ea7476a380ce3924d86 +size 4457767584 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_M.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_M.gguf new file mode 100644 index 0000000..cbdba9e --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71588e99582ff10318f08230716cb0fccb2c6001630c9aa49261f858f111860a +size 5444829856 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_S.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_S.gguf new file mode 100644 index 0000000..3fd5eea --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7577881899879933b0bd1f0c176410354588689c7e9bbd57e26ab91d6a3c055 +size 5315175072 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q6_K.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q6_K.gguf new file mode 100644 index 0000000..b0f42e4 --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91700d82433e4aa52ff756538a2db69dd0d0887ed537aa78b5ec1f68ba944daf +size 6254197408 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.Q8_0.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.Q8_0.gguf new file mode 100644 index 0000000..f04317c --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9449a83f5056e3f078f8a718db6b8585d8c3aa15a96abf7db1981c29c221cb8b +size 8098523808 diff --git a/Qwen2-7B-sft-ultrachat-safeRLHF.f16.gguf b/Qwen2-7B-sft-ultrachat-safeRLHF.f16.gguf new file mode 100644 index 0000000..80e27eb --- /dev/null +++ b/Qwen2-7B-sft-ultrachat-safeRLHF.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:368cf0991732f984b4482a286128e7e59465b1e340e7c4eef3d396db024edb61 +size 15237851808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4abf9f7 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/Qwen2-7B-sft-ultrachat-safeRLHF +language: +- en +library_name: transformers +model_name: Qwen2-7B-sft-ultrachat-safeRLHF +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2-7B-sft-ultrachat-safeRLHF + + +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-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-7B-sft-ultrachat-safeRLHF-GGUF/resolve/main/Qwen2-7B-sft-ultrachat-safeRLHF.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. + +