commit b9717841e4e4f0a92ef1bdbcacc48568b8bcd0c3 Author: ModelHub XC Date: Mon Aug 3 15:53:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..15d2afc --- /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-Aloe-Beta-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Aloe-Beta-7B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Aloe-Beta-7B.IQ4_XS.gguf b/Qwen2.5-Aloe-Beta-7B.IQ4_XS.gguf new file mode 100644 index 0000000..c084f8a --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:841f4820b8e3544fafb91dd5662a68a5ff8f25d04171411364fcf195d212a3fa +size 4250301472 diff --git a/Qwen2.5-Aloe-Beta-7B.Q2_K.gguf b/Qwen2.5-Aloe-Beta-7B.Q2_K.gguf new file mode 100644 index 0000000..6d8b530 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91608dca39e3bc56a99dce0477e6cead7ecd7bd05ef2e0baa1624b3b7f53db77 +size 3015943200 diff --git a/Qwen2.5-Aloe-Beta-7B.Q3_K_L.gguf b/Qwen2.5-Aloe-Beta-7B.Q3_K_L.gguf new file mode 100644 index 0000000..c7e5695 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ce22f916f473b71ba2eefabd347572b22f202ca5639d5cc37ac8e8d563963f6 +size 4088462368 diff --git a/Qwen2.5-Aloe-Beta-7B.Q3_K_M.gguf b/Qwen2.5-Aloe-Beta-7B.Q3_K_M.gguf new file mode 100644 index 0000000..e5edab1 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9d3636719c23f720a0110a4994a66b112b0c830d54e708a750e5598560e427 +size 3808394272 diff --git a/Qwen2.5-Aloe-Beta-7B.Q3_K_S.gguf b/Qwen2.5-Aloe-Beta-7B.Q3_K_S.gguf new file mode 100644 index 0000000..075bf0f --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e39bd6443c9fbd9ea1bea635c4b93d6ba44ab2f2577e12a4a427c1d51bf452 +size 3492371488 diff --git a/Qwen2.5-Aloe-Beta-7B.Q4_0_4_4.gguf b/Qwen2.5-Aloe-Beta-7B.Q4_0_4_4.gguf new file mode 100644 index 0000000..a3ad120 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5e92540a12c8e5f81951cc950c8035f5035f830c1c5ae05ad7d3402420fdf68 +size 4431393824 diff --git a/Qwen2.5-Aloe-Beta-7B.Q4_K_M.gguf b/Qwen2.5-Aloe-Beta-7B.Q4_K_M.gguf new file mode 100644 index 0000000..b7baba5 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c69c98c464ec0ec018143c240848522734ed7c7fa41dd6cdd3e980986d99666 +size 4683076640 diff --git a/Qwen2.5-Aloe-Beta-7B.Q4_K_S.gguf b/Qwen2.5-Aloe-Beta-7B.Q4_K_S.gguf new file mode 100644 index 0000000..ff67b49 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e263f3cc3585e836bd61ea36b572862da518b79b06d1bc5c70664d9eed6ebd4 +size 4457772064 diff --git a/Qwen2.5-Aloe-Beta-7B.Q5_K_M.gguf b/Qwen2.5-Aloe-Beta-7B.Q5_K_M.gguf new file mode 100644 index 0000000..8ae0dc0 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939914e8edcf0fbb5806a1edef48c38ac2b15d2dff55d623781e6f6ab52e637d +size 5444834336 diff --git a/Qwen2.5-Aloe-Beta-7B.Q5_K_S.gguf b/Qwen2.5-Aloe-Beta-7B.Q5_K_S.gguf new file mode 100644 index 0000000..840f4ff --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c83aeea413e5a47abab2e926a94f1c3b47509a5c94dfcd283fa42c12374bb0 +size 5315179552 diff --git a/Qwen2.5-Aloe-Beta-7B.Q6_K.gguf b/Qwen2.5-Aloe-Beta-7B.Q6_K.gguf new file mode 100644 index 0000000..e952e71 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c506f037ad5b856c584094d2ee695f055a9292ae474b191fce9966744eebae3 +size 6254201888 diff --git a/Qwen2.5-Aloe-Beta-7B.Q8_0.gguf b/Qwen2.5-Aloe-Beta-7B.Q8_0.gguf new file mode 100644 index 0000000..3312225 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5aa758dae8f885900d508ed61fb6b3d30de2c983912bbb3f1ccd9ba942ffcce +size 8098528288 diff --git a/Qwen2.5-Aloe-Beta-7B.f16.gguf b/Qwen2.5-Aloe-Beta-7B.f16.gguf new file mode 100644 index 0000000..a254089 --- /dev/null +++ b/Qwen2.5-Aloe-Beta-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06831b796a0efcb44393f0fb58a527d5889350c9c62ed20c994cfc7fe13a8b69 +size 15237856288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bc3303d --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: HPAI-BSC/Qwen2.5-Aloe-Beta-7B +datasets: +- HPAI-BSC/Aloe-Beta-General-Collection +- HPAI-BSC/chain-of-diagnosis +- HPAI-BSC/MedS-Ins +- HPAI-BSC/ultramedical +- HPAI-BSC/pubmedqa-cot-llama31 +- HPAI-BSC/medqa-cot-llama31 +- HPAI-BSC/medmcqa-cot-llama31 +- HPAI-BSC/headqa-cot-llama31 +- HPAI-BSC/MMLU-medical-cot-llama31 +- HPAI-BSC/Polymed-QA +- HPAI-BSC/Aloe-Beta-General-Collection +- HPAI-BSC/Aloe-Beta-General-Collection +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- biology +- medical +- healthcare +--- +## About + + + + + + +static quants of https://huggingface.co/HPAI-BSC/Qwen2.5-Aloe-Beta-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-Aloe-Beta-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-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-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Aloe-Beta-7B-GGUF/resolve/main/Qwen2.5-Aloe-Beta-7B.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. + +