commit 84918d5874201150dfb1b38b97e71f56e7e8b730 Author: ModelHub XC Date: Wed May 13 13:40:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eec15f1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.IQ4_XS.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.IQ4_XS.gguf new file mode 100644 index 0000000..36b8a96 --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5a4e085ce12973cf5019ab7d634f5a7748e609bd64a07742a5a096c4ec3637 +size 8186193760 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q2_K.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q2_K.gguf new file mode 100644 index 0000000..35f58a4 --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a97aa501bce823b7c8bae89451fd138e8e2df87fa64b6e6c6273d37a86a7414 +size 5770495840 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_L.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_L.gguf new file mode 100644 index 0000000..e738242 --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6247f355e70978129350b46527f612c2691be0670d71a9da032febe95d2d11 +size 7924766560 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_M.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_M.gguf new file mode 100644 index 0000000..6df8732 --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:018e7290721f4e9ed97c0e8f2c9d6bff73ef68f702d4db9756844027680a6f00 +size 7339202400 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_S.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_S.gguf new file mode 100644 index 0000000..c8bd0c4 --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5936b13af69f08bb0f76cd31031fc1bd617e28be5667fc82330b7cf7307d4496 +size 6659594080 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_M.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_M.gguf new file mode 100644 index 0000000..ce4f014 --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3543bb359f87b8e19d9e8754217da5be455e2cadc432c914a64c6553d0d2b119 +size 8988108640 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_S.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_S.gguf new file mode 100644 index 0000000..b33855a --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:704651b11e77e315198f52b6c1210ae44afd8a965df7f750e1526fd230afee06 +size 8573429600 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_M.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_M.gguf new file mode 100644 index 0000000..e3b4920 --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe604550d2c6e216c8eb3bd0053856254c8c7f335a62342bf35281f61a0b3fa +size 10508871520 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_S.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_S.gguf new file mode 100644 index 0000000..aaf3c2f --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4342444e027274f46a47747abda5c2c9fd5744605f592ceb6e53ad8db886d542 +size 10266552160 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q6_K.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q6_K.gguf new file mode 100644 index 0000000..2a6a90c --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef0937d11d0b2b8a509ea3b58a25df873fd99d1362a8ec5ecf57aa4da2503c4 +size 12124682080 diff --git a/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q8_0.gguf b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q8_0.gguf new file mode 100644 index 0000000..2d932e8 --- /dev/null +++ b/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e076df42b8a442270d63ede8f7333b5c3970721e7b4eeb7395f47248c193d15e +size 15701596000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1129fef --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: rafaelteste/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot +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/rafaelteste/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-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_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q2_K.gguf) | Q2_K | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_S.gguf) | Q3_K_S | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q3_K_L.gguf) | Q3_K_L | 8.0 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.IQ4_XS.gguf) | IQ4_XS | 8.3 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_S.gguf) | Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q5_K_M.gguf) | Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q6_K.gguf) | Q6_K | 12.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot-GGUF/resolve/main/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality | + +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. + +