commit 579dad55c4bd8accc9a40b7a8314cf440179d4d1 Author: ModelHub XC Date: Thu Jul 16 15:35:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-UMLS-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2f93b9b --- /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-UMLS-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-UMLS-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-UMLS-7B-Instruct.IQ4_XS.gguf b/Qwen-UMLS-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..91867ea --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca66588a8f38edc081d5e733bc09626404bd1b6699e6b2d78f183f339fadbfc +size 4250299648 diff --git a/Qwen-UMLS-7B-Instruct.Q2_K.gguf b/Qwen-UMLS-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..7e81e9d --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba410c0119de304e2ec0990973ff341933d4b654a0f15afa36068f8c6c97e7de +size 3015941376 diff --git a/Qwen-UMLS-7B-Instruct.Q3_K_L.gguf b/Qwen-UMLS-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..0dffdf2 --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce6abc8bb6ad17598867ef9105ed4c40be1e8d03f435d99965ef9ad0862cdfd8 +size 4088460544 diff --git a/Qwen-UMLS-7B-Instruct.Q3_K_M.gguf b/Qwen-UMLS-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..a11f2a5 --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b68fa13d2849fdade5fefab61c5a9a287142fc16c8ed4e9ef1e13e485244ff +size 3808392448 diff --git a/Qwen-UMLS-7B-Instruct.Q3_K_S.gguf b/Qwen-UMLS-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..bdbd9a1 --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47e42d49a074c50ccaad544b185ab832fcb11a4f70d81a71b510dada656816d +size 3492369664 diff --git a/Qwen-UMLS-7B-Instruct.Q4_K_M.gguf b/Qwen-UMLS-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..c9928cd --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef2a664b5ba58df759381ab6ba252b39ea265416df3a2495d64fe5599e737a7 +size 4683074816 diff --git a/Qwen-UMLS-7B-Instruct.Q4_K_S.gguf b/Qwen-UMLS-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..6a471c0 --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d2578aae63bc68a3e49fd7f454a8aea5b1858e29523d70ca16fb1014f5cbb0b +size 4457770240 diff --git a/Qwen-UMLS-7B-Instruct.Q5_K_M.gguf b/Qwen-UMLS-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..a3a9373 --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73199d6d7543ba1a724f98b45c1ec154079b1d226a27b32105da1db5efeaeba9 +size 5444832512 diff --git a/Qwen-UMLS-7B-Instruct.Q5_K_S.gguf b/Qwen-UMLS-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..8eaade7 --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a24b21e3da49777f908e7c2579fce533935044d0b99c52082536f6373c1037f +size 5315177728 diff --git a/Qwen-UMLS-7B-Instruct.Q6_K.gguf b/Qwen-UMLS-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..f0ecb7d --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1ba193f4e09a6efa86543944f40ee7e69c38e871e3a66876f68d3e849f91081 +size 6254200064 diff --git a/Qwen-UMLS-7B-Instruct.Q8_0.gguf b/Qwen-UMLS-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..ddc744f --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4502c59a5933802d08db10ead5cea0ee98fa601a33e4c38beef6771d0bba36b +size 8098526464 diff --git a/Qwen-UMLS-7B-Instruct.f16.gguf b/Qwen-UMLS-7B-Instruct.f16.gguf new file mode 100644 index 0000000..4b397ac --- /dev/null +++ b/Qwen-UMLS-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e2778d6636e32bd7fa7b1d9f360ef1228a3944361f5488fb0837769ff5d2e1 +size 15237854464 diff --git a/README.md b/README.md new file mode 100644 index 0000000..61a6503 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: prithivMLmods/Qwen-UMLS-7B-Instruct +datasets: +- avaliev/umls +language: +- en +library_name: transformers +license: creativeml-openrail-m +quantized_by: mradermacher +tags: +- safetensors +- Unified Medical Language System +- Qwen2.5 +- 7B +- Instruct +- Medical +- text-generation-inference +- National Library of Medicine +- umls +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Qwen-UMLS-7B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen-UMLS-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/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-7B-Instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-UMLS-7B-Instruct-GGUF/resolve/main/Qwen-UMLS-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. + +