commit 7b885a60305a67fb26cc772346a1e9d5e74d1c87 Author: ModelHub XC Date: Tue Jun 2 13:46:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..106c016 --- /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 +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Medical-Expert.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.IQ4_XS.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.IQ4_XS.gguf new file mode 100644 index 0000000..e0914ab --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d7d6b5e00f8a7b50444585639f61e8dc0340f12a667a2bea54665806eefdc7 +size 4484366368 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q2_K.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q2_K.gguf new file mode 100644 index 0000000..be6a30a --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ef950e778617afd983166a74b0c2ed53dfcd532eecac77823a2bccbfda7f4b +size 3179135008 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_L.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_L.gguf new file mode 100644 index 0000000..3c6ae0c --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1678949addf442a1a977639b88e39375902c4f66467d9d397197371c653eb206 +size 4321959968 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_M.gguf new file mode 100644 index 0000000..2bd52be --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c293c50bc0ced7153a3ffbc7796d21f20d57037ceaee2421cc76d1979544257a +size 4018921504 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_S.gguf new file mode 100644 index 0000000..0c7b209 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f475c796f8ddf74d09328da018ff50fd1c05304942ed8bb5396e453a2bcf03a +size 3664502816 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_M.gguf new file mode 100644 index 0000000..25bb247 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df25534a4bcb3af54c0644ec4f873c7051cdcf9c5fc5c4b597ad4ab721a2437 +size 4920737824 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_S.gguf new file mode 100644 index 0000000..fd7fbdc --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24d3d2af333ec520fddaea304aa708b555426306fc3b1b02206dc2607cbcef8 +size 4692672544 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_M.gguf new file mode 100644 index 0000000..f3b74f9 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b29d9420a11de379a583236978d9dce6a40ac31310f59c1a75255a62a28cba +size 5732991008 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_S.gguf new file mode 100644 index 0000000..4f6e6ae --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eacefedba9675178cfa29df142b59f724d91a82c775204613abcf1f26301378a +size 5599297568 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q6_K.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q6_K.gguf new file mode 100644 index 0000000..71eba34 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadaf15513d284b1372463f1926410ac27a746682e6cf35f38aa0fa378427a2b +size 6596010016 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q8_0.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q8_0.gguf new file mode 100644 index 0000000..24187b5 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0518f7fe085880e978290ddce8d269204e1719b21936510b10648019330018a1 +size 8540774432 diff --git a/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.f16.gguf b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.f16.gguf new file mode 100644 index 0000000..fc5e5f8 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a116524774bb06b9a710417542daf18a2b4082e4988aeb7d054cd40a95bdc50 +size 16068894752 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fb0830f --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: vignesha7/DeepSeek-R1-Distill-Llama-8B-Medical-Expert +datasets: +- FreedomIntelligence/medical-o1-reasoning-SFT +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/vignesha7/DeepSeek-R1-Distill-Llama-8B-Medical-Expert + + +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/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Medical-Expert-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Medical-Expert.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. + +