commit 41d966ba4af27198894b78b217ae8d20bb557312 Author: ModelHub XC Date: Tue Sep 1 14:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..47916cb --- /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 +8-bit_medical_Qwen1.5-7B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +8-bit_medical_Qwen1.5-7B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/8-bit_medical_Qwen1.5-7B-Chat.IQ4_XS.gguf b/8-bit_medical_Qwen1.5-7B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..e551cd2 --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc28f67777b1f89615da85c032ee40a957e63865e266035f41b3cae264acf98 +size 4318265664 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q2_K.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q2_K.gguf new file mode 100644 index 0000000..8382cbe --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe5c6ab62a1cc36665fcb57b65b5a72266a6bcd5aa8ef0a893f77fb7d8c2f878 +size 3103826240 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_L.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..0802bba --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8fc3aabef3ec643eadfbac4794956a2fd2ffb3110081e37e0f5936f6531f833 +size 4217966912 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_M.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..308ab72 --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bc2d7fa2bcd315d86ca36937fbc74b60d22ff5a66c8b7b507febfdebb713ebf +size 3918860608 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_S.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..0daaab7 --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46f0b91134c82cf3190eebe51d4ca1bfb9f05d211963f608001809e0d656cc30 +size 3569160512 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q4_K_M.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..4505c00 --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea260ce4cb9eb96ab0284aabb03b7b489c30a84d95341fd51ae66cd8107e987 +size 4767105344 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q4_K_S.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..5e0d606 --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f1587be740026483ca5e9bc914220e7a5e51368e7ba188304a4a047ae04a8f +size 4542841152 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q5_K_M.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..72b4a59 --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54128f0ecb070f791b2f7010ae4f56ed5968064a1cd45a414b0a0b2f32953aba +size 5530665280 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q5_K_S.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..3cfc0ca --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6e6cdef72edddf647ef56eaf1b26b9c4c81c2954d99a3d3b7fcc92170fad73 +size 5399200064 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q6_K.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q6_K.gguf new file mode 100644 index 0000000..0060da3 --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a2a178de99b28172f09be059711e4075a3bd7f2d9b778a2c69e0e0ec3d824d +size 6341947712 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.Q8_0.gguf b/8-bit_medical_Qwen1.5-7B-Chat.Q8_0.gguf new file mode 100644 index 0000000..0b96333 --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3026b6f7dff1a6cf0ddbc41dee1a4a4530fb9305a76bef46c9facf00239efad +size 8211796288 diff --git a/8-bit_medical_Qwen1.5-7B-Chat.f16.gguf b/8-bit_medical_Qwen1.5-7B-Chat.f16.gguf new file mode 100644 index 0000000..a1bb104 --- /dev/null +++ b/8-bit_medical_Qwen1.5-7B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dd2fb9baeac1bf3b14d830c4c57b50f0bfa5ff5c33426d26da661eea3562e31 +size 15449919808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ef60624 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Roselia-penguin/8-bit_medical_Qwen1.5-7B-Chat +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- medical +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/Roselia-penguin/8-bit_medical_Qwen1.5-7B-Chat + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#8-bit_medical_Qwen1.5-7B-Chat-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-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/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q3_K_L.gguf) | Q3_K_L | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q5_K_M.gguf) | Q5_K_M | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.Q8_0.gguf) | Q8_0 | 8.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/8-bit_medical_Qwen1.5-7B-Chat-GGUF/resolve/main/8-bit_medical_Qwen1.5-7B-Chat.f16.gguf) | f16 | 15.5 | 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. + +