commit 24b0e598e6ba652ba84ef637ee888f3b5984baf9 Author: ModelHub XC Date: Sun Jun 14 21:55:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88ce7ff --- /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-Osiris-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Osiris-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Osiris-7B-Instruct.IQ4_XS.gguf b/Qwen2.5-Osiris-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..cdc8116 --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84ab865830a1a577381828ae1f22420e734d8d3fe5f294d0f39c62204d5aa59d +size 4250299168 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q2_K.gguf b/Qwen2.5-Osiris-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..8ee56ef --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d38467f2b56ec1a56ebd9cd586e68d91bdcba5ec0a6139f1081d5a9610de65a +size 3015940896 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q3_K_L.gguf b/Qwen2.5-Osiris-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..dd5e52c --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2f6933b53140557b5a79d95616bd3ca9f7a6cfe6ce6ce27e9b86fbda26d3c8 +size 4088460064 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q3_K_M.gguf b/Qwen2.5-Osiris-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..1306023 --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d85d6032380dfe238b09783a29a62eb55006b34a20013f1466764c9d046822a +size 3808391968 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q3_K_S.gguf b/Qwen2.5-Osiris-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..c659549 --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab0eef1acdff1cf608a7ce5841b4264bea9ce35612389dc0d3bf52848b328fe +size 3492369184 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q4_K_M.gguf b/Qwen2.5-Osiris-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..5bb251b --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4f93069f79f60c00d8bdf2f29ef73945741f113f30d537e98dc40ef65adaff +size 4683074336 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q4_K_S.gguf b/Qwen2.5-Osiris-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..cf91134 --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d59fcea9b7185b12655135bd0d2485ded642d9475d97619f4d12224d862fadc +size 4457769760 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q5_K_M.gguf b/Qwen2.5-Osiris-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..bb3dfda --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f066e991e38a393c76f8308e9f058633d472c0fa891b154fe622e25a3d8c63e +size 5444832032 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q5_K_S.gguf b/Qwen2.5-Osiris-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..29ce27e --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:694ffbae39ce9efb8dced7242754416c3709ca09feafa8ef3600b996f7769fb9 +size 5315177248 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q6_K.gguf b/Qwen2.5-Osiris-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..3b4b111 --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c72ddafc62f013e806249d0bb5fa4054dffc0b1da8639e8a64c62b120786f83 +size 6254199584 diff --git a/Qwen2.5-Osiris-7B-Instruct.Q8_0.gguf b/Qwen2.5-Osiris-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..57ea68c --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6427462459b8637e4c89a1132d9de1a325a18d3b014322ba31d8f3bf6e7079b +size 8098525984 diff --git a/Qwen2.5-Osiris-7B-Instruct.f16.gguf b/Qwen2.5-Osiris-7B-Instruct.f16.gguf new file mode 100644 index 0000000..d903a0b --- /dev/null +++ b/Qwen2.5-Osiris-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c5ee31a29df7b03825a05810c4af49c8efaf79c8f20f47bd890d04b7aa12fd +size 15237853984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..362bb68 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: judgmentlabs/Qwen2.5-Osiris-7B-Instruct +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/judgmentlabs/Qwen2.5-Osiris-7B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-Osiris-7B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-i1-GGUF +## 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-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Osiris-7B-Instruct-GGUF/resolve/main/Qwen2.5-Osiris-7B-Instruct.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. + +