commit 0da71056b11f7b109a372ea1a9d87682a93da024 Author: ModelHub XC Date: Mon Jun 22 23:32:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama2-MedTuned-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..64aa78d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Llama2-MedTuned-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-MedTuned-7b.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama2-MedTuned-7b.IQ4_XS.gguf b/Llama2-MedTuned-7b.IQ4_XS.gguf new file mode 100644 index 0000000..4a7f757 --- /dev/null +++ b/Llama2-MedTuned-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf270a74aa674293d4e6fcc7afae8b38cd060ffa39548a47e40954c33e52ccf +size 3647517216 diff --git a/Llama2-MedTuned-7b.Q2_K.gguf b/Llama2-MedTuned-7b.Q2_K.gguf new file mode 100644 index 0000000..25615df --- /dev/null +++ b/Llama2-MedTuned-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07beba1a5a88864e3853d4642f2063219f09c88462e4b512b2e4c53d9e6c6719 +size 2532864544 diff --git a/Llama2-MedTuned-7b.Q3_K_L.gguf b/Llama2-MedTuned-7b.Q3_K_L.gguf new file mode 100644 index 0000000..d983ef3 --- /dev/null +++ b/Llama2-MedTuned-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1627c4170aa2ff5537e010d95625188fa42b80b34ca72a0dd31945b9a1ba4d +size 3597111840 diff --git a/Llama2-MedTuned-7b.Q3_K_M.gguf b/Llama2-MedTuned-7b.Q3_K_M.gguf new file mode 100644 index 0000000..d6829f7 --- /dev/null +++ b/Llama2-MedTuned-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea647b35ebc8dd2d55a8d4b45d0d631bc68911418fe516f5f26585ea005444f +size 3298005536 diff --git a/Llama2-MedTuned-7b.Q3_K_S.gguf b/Llama2-MedTuned-7b.Q3_K_S.gguf new file mode 100644 index 0000000..9739d99 --- /dev/null +++ b/Llama2-MedTuned-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b29e8e651ea237a97f3e71e965c7e97900192fe89f351fba2d40d3d7ab5d35d +size 2948305440 diff --git a/Llama2-MedTuned-7b.Q4_0_4_4.gguf b/Llama2-MedTuned-7b.Q4_0_4_4.gguf new file mode 100644 index 0000000..d171f33 --- /dev/null +++ b/Llama2-MedTuned-7b.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:451cd936116816c41dd91f4dcb7f8c99ec9eca7ab03923e00a95a804b065dec8 +size 3825807904 diff --git a/Llama2-MedTuned-7b.Q4_K_M.gguf b/Llama2-MedTuned-7b.Q4_K_M.gguf new file mode 100644 index 0000000..74db03e --- /dev/null +++ b/Llama2-MedTuned-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a65f9f62e1e94fde4505361b06117bc3a1d1d880f659280df80775a631e0f42e +size 4081005088 diff --git a/Llama2-MedTuned-7b.Q4_K_S.gguf b/Llama2-MedTuned-7b.Q4_K_S.gguf new file mode 100644 index 0000000..182cd11 --- /dev/null +++ b/Llama2-MedTuned-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b037b8f07703c1ffaa29fd413addfe100515f10fe6087236b190b77b4bd64a83 +size 3856740896 diff --git a/Llama2-MedTuned-7b.Q5_K_M.gguf b/Llama2-MedTuned-7b.Q5_K_M.gguf new file mode 100644 index 0000000..e57f1ba --- /dev/null +++ b/Llama2-MedTuned-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4eb83459b7b3d1f2cf5971207c17142e1c55d69546b22cd639e912cc411bee3 +size 4783157792 diff --git a/Llama2-MedTuned-7b.Q5_K_S.gguf b/Llama2-MedTuned-7b.Q5_K_S.gguf new file mode 100644 index 0000000..f5873e5 --- /dev/null +++ b/Llama2-MedTuned-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b75cb37ca07d6f6ad005d5be3f9d26be214c3372974f14e86516efc9681b846b +size 4651692576 diff --git a/Llama2-MedTuned-7b.Q6_K.gguf b/Llama2-MedTuned-7b.Q6_K.gguf new file mode 100644 index 0000000..a6d4d1c --- /dev/null +++ b/Llama2-MedTuned-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43a3dd3a7d6c493501443cf17a65f4ae82a48219b953a0a84bde802f233f017a +size 5529195040 diff --git a/Llama2-MedTuned-7b.Q8_0.gguf b/Llama2-MedTuned-7b.Q8_0.gguf new file mode 100644 index 0000000..c6e9b8d --- /dev/null +++ b/Llama2-MedTuned-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcbf1d71dc502f4ebf9c144f19661575f79bd835039ccdd262e1ad69e86e37c +size 7161090592 diff --git a/Llama2-MedTuned-7b.f16.gguf b/Llama2-MedTuned-7b.f16.gguf new file mode 100644 index 0000000..1426d1a --- /dev/null +++ b/Llama2-MedTuned-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f064ac8b1c478718f125ac211e628a096bc26af3a53aee6d3e95759eb79c0ff7 +size 13478105632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a2b4cef --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: nlpie/Llama2-MedTuned-7b +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- biomedical +- clinical +- medical +- oxford-legacy +--- +## About + + + + + + +static quants of https://huggingface.co/nlpie/Llama2-MedTuned-7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama2-MedTuned-7b-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/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-MedTuned-7b-GGUF/resolve/main/Llama2-MedTuned-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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +