commit aff46edae9188115cb2a8452ae97d5a2f800af01 Author: ModelHub XC Date: Fri Jun 26 20:06:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..863e61c --- /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 +Llama2-7B-Medical-Finetune_V2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-7B-Medical-Finetune_V2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama2-7B-Medical-Finetune_V2.IQ4_XS.gguf b/Llama2-7B-Medical-Finetune_V2.IQ4_XS.gguf new file mode 100644 index 0000000..fb05e10 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09016c276f129bd9899be24c56041e369a683fa172f4c8e43a15e9c22a65927e +size 3647518400 diff --git a/Llama2-7B-Medical-Finetune_V2.Q2_K.gguf b/Llama2-7B-Medical-Finetune_V2.Q2_K.gguf new file mode 100644 index 0000000..8e8dd24 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:723a21a677cbfda20dbcbc0362814632f4f9ff9bafa62415cbcc45df4613a69e +size 2532865728 diff --git a/Llama2-7B-Medical-Finetune_V2.Q3_K_L.gguf b/Llama2-7B-Medical-Finetune_V2.Q3_K_L.gguf new file mode 100644 index 0000000..b916216 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5061add62d7f827decc98c05d06aa2bcba2e76904ff15b6b393384156f2e7edf +size 3597113024 diff --git a/Llama2-7B-Medical-Finetune_V2.Q3_K_M.gguf b/Llama2-7B-Medical-Finetune_V2.Q3_K_M.gguf new file mode 100644 index 0000000..424e99d --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06f035f430fbd9d808b18c95694d428c51ed27fc9bb9211edb800ad0b3f4f05 +size 3298006720 diff --git a/Llama2-7B-Medical-Finetune_V2.Q3_K_S.gguf b/Llama2-7B-Medical-Finetune_V2.Q3_K_S.gguf new file mode 100644 index 0000000..c6d8605 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7909219d42695bbc8a41f799b7e3fe3f799569d7a719ad5ca7c46c9329a470 +size 2948306624 diff --git a/Llama2-7B-Medical-Finetune_V2.Q4_0_4_4.gguf b/Llama2-7B-Medical-Finetune_V2.Q4_0_4_4.gguf new file mode 100644 index 0000000..a75a803 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb298638ddc149013647c77db0a56336c35f77f937b1510da40d2f65a823176 +size 3825809088 diff --git a/Llama2-7B-Medical-Finetune_V2.Q4_K_M.gguf b/Llama2-7B-Medical-Finetune_V2.Q4_K_M.gguf new file mode 100644 index 0000000..26cd437 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1933fc31cbc9c400c21ca94ead53efaa2c989902a7d5f50032ecdde85d61ab8 +size 4081006272 diff --git a/Llama2-7B-Medical-Finetune_V2.Q4_K_S.gguf b/Llama2-7B-Medical-Finetune_V2.Q4_K_S.gguf new file mode 100644 index 0000000..0bbdb26 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc7d8be297768d27b7d8665b47bb1c322aa9c7bcdd96612dd7af19ea1cad16f5 +size 3856742080 diff --git a/Llama2-7B-Medical-Finetune_V2.Q5_K_M.gguf b/Llama2-7B-Medical-Finetune_V2.Q5_K_M.gguf new file mode 100644 index 0000000..436ef55 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f76722c5b7584af0d73e4d32aad64a8c551faaeafd987dd2ce1b4cdd20a448a9 +size 4783158976 diff --git a/Llama2-7B-Medical-Finetune_V2.Q5_K_S.gguf b/Llama2-7B-Medical-Finetune_V2.Q5_K_S.gguf new file mode 100644 index 0000000..841b4ef --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25bff39a3777b1cfac23c728a5f5036bd765b23edc65c85c28c93fb58f6a4acc +size 4651693760 diff --git a/Llama2-7B-Medical-Finetune_V2.Q6_K.gguf b/Llama2-7B-Medical-Finetune_V2.Q6_K.gguf new file mode 100644 index 0000000..cafcf2d --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea58592be907c954ad3eab39700a0def8028578dba430395e11bbbab5a4d0322 +size 5529196224 diff --git a/Llama2-7B-Medical-Finetune_V2.Q8_0.gguf b/Llama2-7B-Medical-Finetune_V2.Q8_0.gguf new file mode 100644 index 0000000..d588113 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63ed6d73c37369a3873930e2dc738847b421711a248f3f8e3914e2354061451 +size 7161091776 diff --git a/Llama2-7B-Medical-Finetune_V2.f16.gguf b/Llama2-7B-Medical-Finetune_V2.f16.gguf new file mode 100644 index 0000000..99a74e8 --- /dev/null +++ b/Llama2-7B-Medical-Finetune_V2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16736153f431c429db48f66e9d3e8760503e11e84f6dceef67cc1b6246370435 +size 13478106816 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c0df601 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: TachyHealthResearch/Llama2-7B-Medical-Finetune_V2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- trl +- sft +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/TachyHealthResearch/Llama2-7B-Medical-Finetune_V2 + + +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/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-7B-Medical-Finetune_V2-GGUF/resolve/main/Llama2-7B-Medical-Finetune_V2.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. + +