commit 130d9dab2a990ac280fce81d0131c4ae9a022e84 Author: ModelHub XC Date: Tue May 26 09:58:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f774255 --- /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-Ablation.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Ablation.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.IQ4_XS.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.IQ4_XS.gguf new file mode 100644 index 0000000..7b87a83 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b4619746a1562c2233c09b6cdf26821c74ca0d2994bf48deaf8cea1f779cee1 +size 4484366144 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q2_K.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q2_K.gguf new file mode 100644 index 0000000..2587e9e --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2498aba43f776165e05bace4dff556102c17d0d4f51973c49532df5a6fd9fddc +size 3179134784 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_L.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_L.gguf new file mode 100644 index 0000000..de71b0e --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8292e68a627a2c5c385fd78a89b3dc4a7c87b1d361da2746ac05c50539f73cdb +size 4321959744 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_M.gguf new file mode 100644 index 0000000..458a7d1 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ae5efdad1c4d0e59095879dd5f88f5b219a63423ba71f5cf5df9d5013feb083 +size 4018921280 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_S.gguf new file mode 100644 index 0000000..9e162ed --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30c3f3ee8782bc076d4e1226c0c3cd8f463ac99bf8c1d2c85f9087cbc9d4f143 +size 3664502592 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q4_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q4_K_M.gguf new file mode 100644 index 0000000..eac3d49 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f38ea8c89a56796d87df022a849311b6fa6151da890555d7a8e1f0559acc6c8c +size 4920737600 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q4_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q4_K_S.gguf new file mode 100644 index 0000000..ce8026c --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323ef2471ebe2e2b813fabc4a27154f495c650adfc9db916821eb6d4d1fbc897 +size 4692672320 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_M.gguf new file mode 100644 index 0000000..61aa564 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b406ee7d4ae552060496bd1bf980116b234c6b946eefb24fe1b76889720a076 +size 5732990784 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_S.gguf new file mode 100644 index 0000000..916357a --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcaae431d27f68b731bee2f37388afe1991c17273dcea2105b873f44bda2e963 +size 5599297344 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q6_K.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q6_K.gguf new file mode 100644 index 0000000..849fe35 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b8b7cc97ea8d61941175838111c1668add650d0cdd08c34c7ed8d207632193 +size 6596009792 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.Q8_0.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q8_0.gguf new file mode 100644 index 0000000..f1a889b --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85819087bddcb520c3f01d8fc51ebbdf0d5fab48328dbd0be51ff6b270af9e72 +size 8540774208 diff --git a/DeepSeek-R1-Distill-Llama-8B-Ablation.f16.gguf b/DeepSeek-R1-Distill-Llama-8B-Ablation.f16.gguf new file mode 100644 index 0000000..5d496ff --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Ablation.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18dd5222d456ba3ed07c95f1f89c3e29837cb9d57d49f9be9b4f430cafc4a560 +size 16068894528 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7b65e1d --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: mikkel-werling/DeepSeek-R1-Distill-Llama-8B-Ablation +datasets: mikkel-werling/medqa_ablation +language: +- en +library_name: transformers +model_name: DeepSeek-R1-Distill-Llama-8B-Ablation +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/mikkel-werling/DeepSeek-R1-Distill-Llama-8B-Ablation + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-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/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Ablation-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Ablation.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. + +