commit d1626b4b3c01ae46f73bd3e6b84f551a13bf6442 Author: ModelHub XC Date: Fri Jun 12 21:04:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7a06d8d --- /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-Debiased.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Llama-8B-Debiased.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.IQ4_XS.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.IQ4_XS.gguf new file mode 100644 index 0000000..af4575d --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:233e8cd6f8c7e049bbbf991bc50e56290f5d106e1154be521bb824d834fd8dfa +size 4484365568 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q2_K.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q2_K.gguf new file mode 100644 index 0000000..f0ea6ff --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc1542996ed217505c16d3ede8a22918c5c892df35fd66f6558ee46ab1a433c +size 3179134208 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_L.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_L.gguf new file mode 100644 index 0000000..e25c83f --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef0f589294b1821cd2a426edd2282782dadd2d5aa805ab7e2506105292f3faed +size 4321959168 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_M.gguf new file mode 100644 index 0000000..dd8d35c --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:308e5b57d9e06369dfbc4f1bbb7beb838657bc99f0384a0eeb52505f9e1613e8 +size 4018920704 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_S.gguf new file mode 100644 index 0000000..aaf770d --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b59e9f68e4288e1705aac6866112fa365b5d4161f369f105a005f376472b862a +size 3664502016 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q4_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q4_K_M.gguf new file mode 100644 index 0000000..ea3c201 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d037455e43ca5e922cdf1c504ac46b366a437023bd94d5824f1dcfc15fff8cf +size 4920737024 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q4_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q4_K_S.gguf new file mode 100644 index 0000000..409fef0 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2308f415d49eb80435cfc3ebdcba796aa263cc668d670fa15816106b4ab42784 +size 4692671744 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_M.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_M.gguf new file mode 100644 index 0000000..0186091 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df278defa488fc0a26e35b48a538c1db58b36b5fd268deeaa218ebface34a4f2 +size 5732990208 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_S.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_S.gguf new file mode 100644 index 0000000..b408822 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c329bb4676134f4bed4a77fc757d0d1cf72ff87449b242ccd1db6b1586a78b7 +size 5599296768 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q6_K.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q6_K.gguf new file mode 100644 index 0000000..ee4985d --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a545838700e7ebe5113f7a14c6e0b2e88931e6667de2627b3237666aa55043c3 +size 6596009216 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.Q8_0.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q8_0.gguf new file mode 100644 index 0000000..3d2a633 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:327217c9fe1a0e7b20f483b38a299d0c5c705b18038a59d1a3b8ccfb6825feea +size 8540773632 diff --git a/DeepSeek-R1-Distill-Llama-8B-Debiased.f16.gguf b/DeepSeek-R1-Distill-Llama-8B-Debiased.f16.gguf new file mode 100644 index 0000000..1f32f62 --- /dev/null +++ b/DeepSeek-R1-Distill-Llama-8B-Debiased.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2399c907f639fba3940ee099c1abf8dafce85c4826d1d5cfac106393f8fe0b7b +size 16068893952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..858aafc --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: hirundo-io/DeepSeek-R1-Distill-Llama-8B-Debiased +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/hirundo-io/DeepSeek-R1-Distill-Llama-8B-Debiased + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-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-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Llama-8B-Debiased-GGUF/resolve/main/DeepSeek-R1-Distill-Llama-8B-Debiased.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. + +