commit 274fba5de6ce7433c40f8de45155eff63ead4532 Author: ModelHub XC Date: Sat Apr 11 20:52:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bceb45d --- /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-V3-DRAFT-0.6B-v3.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-V3-DRAFT-0.6B-v3.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.IQ4_XS.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.IQ4_XS.gguf new file mode 100644 index 0000000..13ac69e --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1b65b43f9892aaaa43f533b7be0152f424945c24efad1843ed0d4486bd3d712 +size 394336960 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q2_K.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q2_K.gguf new file mode 100644 index 0000000..cee24d2 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11ae99105b3fa54ebee948f1567e44a4c9c473137dde2ac07c42f62d10679246 +size 381499072 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_L.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_L.gguf new file mode 100644 index 0000000..ea2252d --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:711a9aa9d15dd1751361be54f1ce3d233e7a091b8085dd733c23ec4341834847 +size 412249792 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_M.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_M.gguf new file mode 100644 index 0000000..03a96ab --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f1185b0ef1b46bb8a99b7a469b5a140fecaaab1e2061af62561265fda1c792 +size 398358208 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_S.gguf new file mode 100644 index 0000000..8be6e48 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06d230276e01cc08123a2fd1e0e11b02cbde7bddced380303859efe30802222e +size 381155008 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_M.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_M.gguf new file mode 100644 index 0000000..666a4f6 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da28dbb55c90d5ba8f757b0f0441ed4d95693fa3de9b24eca86704bffaa6085d +size 455178944 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_S.gguf new file mode 100644 index 0000000..c811184 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4de29b2cdcf27194a76ebc901af437e9925653e2ceccb567cb014700431afa +size 442842816 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_M.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_M.gguf new file mode 100644 index 0000000..7e90bea --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78b0c97bc79f7b0ddf36006a7a3e1b074cdf1d1770bb8da5f13c61ffc3513751 +size 484696768 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_S.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_S.gguf new file mode 100644 index 0000000..4218c5f --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e77486ab600f7c713ff1d93d7cd5cb97faa2023e9240f7bbfdd0ba176ead2c72 +size 477320896 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q6_K.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q6_K.gguf new file mode 100644 index 0000000..9a7b445 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a464ca3968b3ed4837b4cf5712acf13d734d5882deb8eeff28f7ba0c04af9a3f +size 606545600 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.Q8_0.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q8_0.gguf new file mode 100644 index 0000000..4f39855 --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b804d51975d90025ba23454b1d59aa0ec37645d68701081fba737d4bd3d95e1d +size 631877312 diff --git a/DeepSeek-V3-DRAFT-0.6B-v3.0.f16.gguf b/DeepSeek-V3-DRAFT-0.6B-v3.0.f16.gguf new file mode 100644 index 0000000..fa5107d --- /dev/null +++ b/DeepSeek-V3-DRAFT-0.6B-v3.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3317d9fd99c2fb5862a1c7265a1a754c6b584605e4574eb043d56bcf8a4cc85b +size 1184530112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e86ee89 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: jukofyork/DeepSeek-V3-DRAFT-0.6B-v3.0 +datasets: +- agentlans/common-crawl-sample +- bigcode/the-stack-smol-xl +- rombodawg/Everything_Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- draft +- speculative-decoding +--- +## About + + + + + + + + + +static quants of https://huggingface.co/jukofyork/DeepSeek-V3-DRAFT-0.6B-v3.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-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-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q5_K_M.gguf) | Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-V3-DRAFT-0.6B-v3.0-GGUF/resolve/main/DeepSeek-V3-DRAFT-0.6B-v3.0.f16.gguf) | f16 | 1.3 | 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. + +