commit 9c3d40838bff047b9edf394ae9a57bdbd19905b3 Author: ModelHub XC Date: Tue Jun 2 13:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..67974c4 --- /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.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Llama-8B.IQ4_XS.gguf b/DeepSeek-R1-Distill-Llama-8B.IQ4_XS.gguf new file mode 100644 index 0000000..9f43fdb --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2ad06951a16503185f5fc8fbc6ba2c621629c142a9ce00d060a290c4d510a8 +size 4484365312 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q2_K.gguf b/DeepSeek-R1-Distill-Llama-8B.Q2_K.gguf new file mode 100644 index 0000000..27580d7 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78f030f3c508b534ada6c7f01d95a1f329fa85759c4ff4d114b07a027d52707 +size 3179133952 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q3_K_L.gguf b/DeepSeek-R1-Distill-Llama-8B.Q3_K_L.gguf new file mode 100644 index 0000000..dc6c4cd --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01bb65286b9ddcee875efb4e4b42197ef49ebc784bdbe69124d8bef3478d306 +size 4321958912 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q3_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B.Q3_K_M.gguf new file mode 100644 index 0000000..4b5015a --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4016b6473ba3cae7082043e7c85e463245835d8c86c34d0dba50820925145c33 +size 4018920448 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q3_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B.Q3_K_S.gguf new file mode 100644 index 0000000..be576f2 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee40d61ff9b17881cae6d3d72c6703928f535a741ce955b87d21684348df61b7 +size 3664501760 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q4_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B.Q4_K_M.gguf new file mode 100644 index 0000000..4728e3b --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b256877558744051a44f004a6d2a6b8296972f48c7e52d1a508dde5f1787733 +size 4920736768 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q4_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B.Q4_K_S.gguf new file mode 100644 index 0000000..b14d2d1 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:213e0d808470ecdad5c04da791576c5c075698915689a1adc679db3a0c5e6fdb +size 4692671488 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q5_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B.Q5_K_M.gguf new file mode 100644 index 0000000..b7a90b6 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9f265bd2f4eba994599dca91a4029a631504b36cdaf0af7514f91ee3d6f82c +size 5732989952 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q5_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B.Q5_K_S.gguf new file mode 100644 index 0000000..a4abce9 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11938c4dee1428c01dbc016df5c2e0832f692d48b1ac7a91bae4123cc3bd6db7 +size 5599296512 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q6_K.gguf b/DeepSeek-R1-Distill-Llama-8B.Q6_K.gguf new file mode 100644 index 0000000..b7f1147 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f90004c320596bbfe1feb0eebefecbec14ab5bdd1b6044e15bcffe2888ecffa5 +size 6596008960 diff --git a/DeepSeek-R1-Distill-Llama-8B.Q8_0.gguf b/DeepSeek-R1-Distill-Llama-8B.Q8_0.gguf new file mode 100644 index 0000000..74eb246 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48eb8905a05c1f6b469e5afe56dd463e79b838d1474af227d59f9d7779887a7a +size 8540773376 diff --git a/DeepSeek-R1-Distill-Llama-8B.f16.gguf b/DeepSeek-R1-Distill-Llama-8B.f16.gguf new file mode 100644 index 0000000..330d751 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba52c1886622b7fcf920a6f7e1f0a3cf64f915655da54cf3b9a3b52da192609f +size 16068893696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..583b180 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-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-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-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. + +