commit 1184c1d64d78a809aab60fe2fd169dd251b9a548 Author: ModelHub XC Date: Wed Sep 16 07:12:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/EYE-Llama_qa-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bf47ad2 --- /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 +EYE-Llama_qa.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.f16.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EYE-Llama_qa.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EYE-Llama_qa.IQ4_XS.gguf b/EYE-Llama_qa.IQ4_XS.gguf new file mode 100644 index 0000000..cf4be36 --- /dev/null +++ b/EYE-Llama_qa.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:152d0398f1aaf415f861714b45fb6152b17f801048018450c31bb489a8756806 +size 3647518368 diff --git a/EYE-Llama_qa.Q2_K.gguf b/EYE-Llama_qa.Q2_K.gguf new file mode 100644 index 0000000..c82ade5 --- /dev/null +++ b/EYE-Llama_qa.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbae3d592b4b109f124278fcf9505c027281e87cab3b30660fba198a5406bbcb +size 2532865696 diff --git a/EYE-Llama_qa.Q3_K_L.gguf b/EYE-Llama_qa.Q3_K_L.gguf new file mode 100644 index 0000000..489edee --- /dev/null +++ b/EYE-Llama_qa.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b66062af54dbcf513c2308795670d6c372d3e31eb2ffdc8adb9bafbcea4bb6 +size 3597112992 diff --git a/EYE-Llama_qa.Q3_K_M.gguf b/EYE-Llama_qa.Q3_K_M.gguf new file mode 100644 index 0000000..d1e4963 --- /dev/null +++ b/EYE-Llama_qa.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2c8176f19a88ce8bd5ad1b5ebf091e4991a2695078c702f7141b71dad8ad4dd +size 3298006688 diff --git a/EYE-Llama_qa.Q3_K_S.gguf b/EYE-Llama_qa.Q3_K_S.gguf new file mode 100644 index 0000000..ae20a8b --- /dev/null +++ b/EYE-Llama_qa.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f9bc2a00d5064622093d51505d68dd27ed02023511b896fe86a226ad1b4ee32 +size 2948306592 diff --git a/EYE-Llama_qa.Q4_K_M.gguf b/EYE-Llama_qa.Q4_K_M.gguf new file mode 100644 index 0000000..a4756ef --- /dev/null +++ b/EYE-Llama_qa.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d394c7a86db6ae418bddd401dda9865f69222747ff37384fcd4a724575067582 +size 4081006240 diff --git a/EYE-Llama_qa.Q4_K_S.gguf b/EYE-Llama_qa.Q4_K_S.gguf new file mode 100644 index 0000000..5871840 --- /dev/null +++ b/EYE-Llama_qa.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9065876b2490108762e6b05b9c9c6a12e3dbc3c5d0135721186b9cc238be18f8 +size 3856742048 diff --git a/EYE-Llama_qa.Q5_K_M.gguf b/EYE-Llama_qa.Q5_K_M.gguf new file mode 100644 index 0000000..bfebe27 --- /dev/null +++ b/EYE-Llama_qa.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2dd024f63c6f8d9191e3e3a7a6187327018600b846f11ccf0c63beea406072 +size 4783158944 diff --git a/EYE-Llama_qa.Q5_K_S.gguf b/EYE-Llama_qa.Q5_K_S.gguf new file mode 100644 index 0000000..cc678b3 --- /dev/null +++ b/EYE-Llama_qa.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907ba9ae1e67d7dcac46847ad141962b239762c887828cdbde84a657fe717f98 +size 4651693728 diff --git a/EYE-Llama_qa.Q6_K.gguf b/EYE-Llama_qa.Q6_K.gguf new file mode 100644 index 0000000..5e82d1f --- /dev/null +++ b/EYE-Llama_qa.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f995570a2bb39766c582898df384d79818fa7ae56ea2f20185a0259042b502 +size 5529196192 diff --git a/EYE-Llama_qa.Q8_0.gguf b/EYE-Llama_qa.Q8_0.gguf new file mode 100644 index 0000000..26847b5 --- /dev/null +++ b/EYE-Llama_qa.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f120bb36fc4adc2d3a328f2526b31a4bd302744e52f2e360361741fb3bdd8f0d +size 7161091744 diff --git a/EYE-Llama_qa.f16.gguf b/EYE-Llama_qa.f16.gguf new file mode 100644 index 0000000..0593231 --- /dev/null +++ b/EYE-Llama_qa.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6033ba9a0df8e97c6e77fa00e70adc7d725b1da4aadcd0687afa5cc7cc898950 +size 13478106784 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6b20c06 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: QIAIUNCC/EYE-Llama_qa +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- medical +--- +## About + + + + + + +static quants of https://huggingface.co/QIAIUNCC/EYE-Llama_qa + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#EYE-Llama_qa-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/EYE-Llama_qa-GGUF/resolve/main/EYE-Llama_qa.f16.gguf) | f16 | 13.6 | 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. + +