commit ab6167fa73a2ae3658b0f1307930d613b43871a3 Author: ModelHub XC Date: Thu Jun 4 14:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Medical-COT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2e14018 --- /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 +Qwen2.5-7B-Medical-COT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Medical-COT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Medical-COT.IQ4_XS.gguf b/Qwen2.5-7B-Medical-COT.IQ4_XS.gguf new file mode 100644 index 0000000..347eec0 --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348f2a3f68d6071426dd4977f1e441c5d023d8311c11e59eb3aaa243e777a0d1 +size 4250299296 diff --git a/Qwen2.5-7B-Medical-COT.Q2_K.gguf b/Qwen2.5-7B-Medical-COT.Q2_K.gguf new file mode 100644 index 0000000..1672703 --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a816719e75b8eb89f53787ffee64c9cbc7656de84bfb5b2128ee13973a46be8b +size 3015941024 diff --git a/Qwen2.5-7B-Medical-COT.Q3_K_L.gguf b/Qwen2.5-7B-Medical-COT.Q3_K_L.gguf new file mode 100644 index 0000000..d635ee7 --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61d3c965517f283f52c1b72804a6444b2b6596128b3c3b91b18e92ab9169604 +size 4088460192 diff --git a/Qwen2.5-7B-Medical-COT.Q3_K_M.gguf b/Qwen2.5-7B-Medical-COT.Q3_K_M.gguf new file mode 100644 index 0000000..7220527 --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c42a224865c5926aabb2422326a5b3ffa45bde975bded9bb2eab0449ae28c9e7 +size 3808392096 diff --git a/Qwen2.5-7B-Medical-COT.Q3_K_S.gguf b/Qwen2.5-7B-Medical-COT.Q3_K_S.gguf new file mode 100644 index 0000000..c75825a --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b196a1679521fffa66bbfdb6ebc140de37698af4f89aef438dd36ee0e97124ad +size 3492369312 diff --git a/Qwen2.5-7B-Medical-COT.Q4_K_M.gguf b/Qwen2.5-7B-Medical-COT.Q4_K_M.gguf new file mode 100644 index 0000000..950ca99 --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93bd8ec44a38df383d92ccae85f46ee9ea18381e2310f03ce880c2cb90e0b8e2 +size 4683074464 diff --git a/Qwen2.5-7B-Medical-COT.Q4_K_S.gguf b/Qwen2.5-7B-Medical-COT.Q4_K_S.gguf new file mode 100644 index 0000000..05aca84 --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b700a1da76d53a15f8d8bc65f99903f24ad2cc3f91638bc48240450a336a9de +size 4457769888 diff --git a/Qwen2.5-7B-Medical-COT.Q5_K_M.gguf b/Qwen2.5-7B-Medical-COT.Q5_K_M.gguf new file mode 100644 index 0000000..ad52830 --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2717df3bedd5679c74ee9871ffeaa8cd2c0cad200c514795bb81df52d88aaef0 +size 5444832160 diff --git a/Qwen2.5-7B-Medical-COT.Q5_K_S.gguf b/Qwen2.5-7B-Medical-COT.Q5_K_S.gguf new file mode 100644 index 0000000..72e51cb --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53220eadb086cb7211b4a9ebb32261ca1aa5451532073fba7bfc9faf5a6a912 +size 5315177376 diff --git a/Qwen2.5-7B-Medical-COT.Q6_K.gguf b/Qwen2.5-7B-Medical-COT.Q6_K.gguf new file mode 100644 index 0000000..2ba8abf --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ac5ce5d340909d6dd723a3afc3fee275e288bbad2dc4b857aeee753ffcc0c3 +size 6254199712 diff --git a/Qwen2.5-7B-Medical-COT.Q8_0.gguf b/Qwen2.5-7B-Medical-COT.Q8_0.gguf new file mode 100644 index 0000000..92fe521 --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d35bfedb6af6ed957e402a6be361a739878e88d763dfeecf5c2ffdcac0e1bc6 +size 8098526112 diff --git a/Qwen2.5-7B-Medical-COT.f16.gguf b/Qwen2.5-7B-Medical-COT.f16.gguf new file mode 100644 index 0000000..7ab7cb4 --- /dev/null +++ b/Qwen2.5-7B-Medical-COT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1f48ece27d8c95185cff84b484c22d6d7e226649aeef0de7d5ca2aaf691fcd2 +size 15237854112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..66014c8 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: alex-ecm/Qwen2.5-7B-Medical-COT +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/alex-ecm/Qwen2.5-7B-Medical-COT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-Medical-COT-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-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/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Medical-COT-GGUF/resolve/main/Qwen2.5-7B-Medical-COT.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. + +