commit 4c453ea091cb11859a752b30e429dc4dc8de0aa2 Author: ModelHub XC Date: Sun Jul 12 22:46:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Med-nirvana-v1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..af133a5 --- /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 +Med-nirvana-v1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Med-nirvana-v1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Med-nirvana-v1-8B.IQ4_XS.gguf b/Med-nirvana-v1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..0e34010 --- /dev/null +++ b/Med-nirvana-v1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d65e9625ab596b6ccda5c5ac25ca76a95fabf3263bfbafa607698b9fbc4616 +size 4484364416 diff --git a/Med-nirvana-v1-8B.Q2_K.gguf b/Med-nirvana-v1-8B.Q2_K.gguf new file mode 100644 index 0000000..2971ce1 --- /dev/null +++ b/Med-nirvana-v1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a72ac1bac79d10f1f852af715d3378b358b8aaf6e0f2a613282a973022074f2 +size 3179133056 diff --git a/Med-nirvana-v1-8B.Q3_K_L.gguf b/Med-nirvana-v1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..091d950 --- /dev/null +++ b/Med-nirvana-v1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f828e04bd87a565ed177250ed60c208492f5606081772eca79b9ee436b015a6 +size 4321958016 diff --git a/Med-nirvana-v1-8B.Q3_K_M.gguf b/Med-nirvana-v1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..703ef10 --- /dev/null +++ b/Med-nirvana-v1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e4132ba9945dceecdd314e318fe834affd8685eb09ac8697aed1d0f9e792974 +size 4018919552 diff --git a/Med-nirvana-v1-8B.Q3_K_S.gguf b/Med-nirvana-v1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..deb4367 --- /dev/null +++ b/Med-nirvana-v1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465b5c36a36c928fdb8cc995030672e4dc69bd2407da2529b1728b977d2cee09 +size 3664500864 diff --git a/Med-nirvana-v1-8B.Q4_K_M.gguf b/Med-nirvana-v1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..bd643de --- /dev/null +++ b/Med-nirvana-v1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8961be2fee50f144ebec265cbccfa1da42428645e06719ff4dc661a1281a067d +size 4920735872 diff --git a/Med-nirvana-v1-8B.Q4_K_S.gguf b/Med-nirvana-v1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..daed513 --- /dev/null +++ b/Med-nirvana-v1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fcac82c39f48615b19c10f64dbc82d9bf6e5e97537be81d6234d9e712d3dfae +size 4692670592 diff --git a/Med-nirvana-v1-8B.Q5_K_M.gguf b/Med-nirvana-v1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..cbbcebf --- /dev/null +++ b/Med-nirvana-v1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cecacbf6427d58f71bc16a78df842e8f059b4bc443a6fb8a29ac314e0a0f9feb +size 5732989056 diff --git a/Med-nirvana-v1-8B.Q5_K_S.gguf b/Med-nirvana-v1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..33e94c1 --- /dev/null +++ b/Med-nirvana-v1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6222ac867c89c378817a5cb3ff1e064b3562b377f8e6c335ec70e7e5453c2601 +size 5599295616 diff --git a/Med-nirvana-v1-8B.Q6_K.gguf b/Med-nirvana-v1-8B.Q6_K.gguf new file mode 100644 index 0000000..bc503ad --- /dev/null +++ b/Med-nirvana-v1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1426e500cf7de503eda27fd41c69ba2505255f63aad53d002a161cb478ef430 +size 6596008064 diff --git a/Med-nirvana-v1-8B.Q8_0.gguf b/Med-nirvana-v1-8B.Q8_0.gguf new file mode 100644 index 0000000..c0a75fb --- /dev/null +++ b/Med-nirvana-v1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:894157cdf832cb330db90218a490aa36229bcd6822a82a39a1ba1f0af723ca48 +size 8540772480 diff --git a/Med-nirvana-v1-8B.f16.gguf b/Med-nirvana-v1-8B.f16.gguf new file mode 100644 index 0000000..6e1a823 --- /dev/null +++ b/Med-nirvana-v1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2796cdc2e1e194c631a36cbbef528593528a7d4801aa0bf12bae07af59276ed +size 16068892800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..23d1ef6 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Dasun7/Med-nirvana-v1-8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Dasun7/Med-nirvana-v1-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Med-nirvana-v1-8B-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/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Med-nirvana-v1-8B-GGUF/resolve/main/Med-nirvana-v1-8B.f16.gguf) | f16 | 16.2 | 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. + +