commit 52f462b8d44d01478320b0598ba52fbdca9c33e2 Author: ModelHub XC Date: Fri Sep 25 19:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c53bb72 --- /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 +FINETUNED-MEDICAL-LLAMA-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FINETUNED-MEDICAL-LLAMA-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FINETUNED-MEDICAL-LLAMA-7B.IQ4_XS.gguf b/FINETUNED-MEDICAL-LLAMA-7B.IQ4_XS.gguf new file mode 100644 index 0000000..78817ce --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef12af63d9ac83b9c792c0bd2cff76f4960f20778aca937435284469e1984ea3 +size 3647517408 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q2_K.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q2_K.gguf new file mode 100644 index 0000000..397cab1 --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28417aed0307c44769dc98668c82460ba9fbf1aae42c370071b2ef36e252cefb +size 2532864736 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_L.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_L.gguf new file mode 100644 index 0000000..664ab25 --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0ce806bcef22b064ebc7beb6dabeda3bb08175ebf0ac59c7c6881ede672244 +size 3597112032 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_M.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_M.gguf new file mode 100644 index 0000000..b4ebe49 --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2283854fc138e4000cbc8cceca72853418f149d5160606d88129bed98e4a81ea +size 3298005728 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_S.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_S.gguf new file mode 100644 index 0000000..4549b01 --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdff32cf6be69050a956341c725459f6ede7a144af3e12754a2aa81d0e776e37 +size 2948305632 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q4_K_M.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q4_K_M.gguf new file mode 100644 index 0000000..9bacf09 --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60c022dab96fbce7cf6a92f7fd5bb59e0a7b585c216315d2f47a6b8568ab348 +size 4081005280 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q4_K_S.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q4_K_S.gguf new file mode 100644 index 0000000..0528d54 --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63b011b11638c9481110dd32005d5d602cfb0bb3924a32612a859582c1cd2aef +size 3856741088 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q5_K_M.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q5_K_M.gguf new file mode 100644 index 0000000..17d2b45 --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:304962239389141f6ad929a0a16bd5a2e279f20e779703ecfc20926fd3d8daa7 +size 4783157984 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q5_K_S.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q5_K_S.gguf new file mode 100644 index 0000000..114bd59 --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168fa5cf0927bc322b1d1b99630b9c92575fabac6c3d2748d284b1f546043441 +size 4651692768 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q6_K.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q6_K.gguf new file mode 100644 index 0000000..b68960c --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:909aae28ee1db5a699d738ac71eedefd6f9c2ebc178fc7b9c43a65e948ac4234 +size 5529195232 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.Q8_0.gguf b/FINETUNED-MEDICAL-LLAMA-7B.Q8_0.gguf new file mode 100644 index 0000000..553f82d --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c949f298b5b9d05c093c0564d2aa804eb6add7433186b48ddadc974a4ca8b72 +size 7161090784 diff --git a/FINETUNED-MEDICAL-LLAMA-7B.f16.gguf b/FINETUNED-MEDICAL-LLAMA-7B.f16.gguf new file mode 100644 index 0000000..23a6b3b --- /dev/null +++ b/FINETUNED-MEDICAL-LLAMA-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:951dc4faf8b47b7a6236eca06daa89516987999d366332159663931d77a5911b +size 13478105824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1fbf679 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: rhyliieee/FINETUNED-MEDICAL-LLAMA-7B +language: +- en +library_name: transformers +license: cc-by-nc-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/rhyliieee/FINETUNED-MEDICAL-LLAMA-7B + + +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/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FINETUNED-MEDICAL-LLAMA-7B-GGUF/resolve/main/FINETUNED-MEDICAL-LLAMA-7B.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. + +