commit 66ab1d1b501b3b6546d9c2e640d92696fe053efe Author: ModelHub XC Date: Wed Jun 3 22:55:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ba38854 --- /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 +Llama3.1-TitanDeluxe-8B-slerp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-TitanDeluxe-8B-slerp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-TitanDeluxe-8B-slerp.IQ4_XS.gguf b/Llama3.1-TitanDeluxe-8B-slerp.IQ4_XS.gguf new file mode 100644 index 0000000..e6b4a34 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b39932ce95fbad769ea912608d71500c749625080dbe589b0be2dbc0491308 +size 4484364000 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q2_K.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q2_K.gguf new file mode 100644 index 0000000..1f240b5 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd2839c190827987328eb4eb49ea2b2d66890b967b400849509cb1ddc9207e7 +size 3179132640 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_L.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_L.gguf new file mode 100644 index 0000000..8588368 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:338c7ab58a8a1740ba067a3caf95a0decb7f7f94431593c0a84dc344ae9c1a72 +size 4321957600 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_M.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_M.gguf new file mode 100644 index 0000000..117b2c4 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fba2586961bbc11385d62868848af3a20c5d3b13377dcd3fc482ade155c3f5c +size 4018919136 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_S.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_S.gguf new file mode 100644 index 0000000..46dfd96 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d8f9cdcd24054652cbacec607ea0959cc572a7933c94ca38d48d32e54b5689 +size 3664500448 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q4_K_M.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q4_K_M.gguf new file mode 100644 index 0000000..ac47cad --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aab6d877eb4d560628c502b439f17d406c1d86eb053a54e5b4f138401b08157a +size 4920735456 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q4_K_S.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q4_K_S.gguf new file mode 100644 index 0000000..10c58f8 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eee87f3ccb489d0b1d90fc4f39daed31530c48c6c61b37393d946cdcbe21d7e4 +size 4692670176 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q5_K_M.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q5_K_M.gguf new file mode 100644 index 0000000..52eb39c --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ac76050731847e2856e1dcf6842d7a134cc45bb5003760bc4106e14ac818dc +size 5732988640 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q5_K_S.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q5_K_S.gguf new file mode 100644 index 0000000..fa5e295 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cef5aa2b86c275ef738155569eff92ac012d2f3f8b6fce4547410e3638e6980 +size 5599295200 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q6_K.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q6_K.gguf new file mode 100644 index 0000000..ccc4824 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ddee49619624104456b762fc305e1631d8bb49b0ac7400494a935a198a682d2 +size 6596007648 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.Q8_0.gguf b/Llama3.1-TitanDeluxe-8B-slerp.Q8_0.gguf new file mode 100644 index 0000000..4c03e33 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9af9a74ba16cacebe169ad12e297f5bef2defccb8123b9c058c71fba4755084 +size 8540772064 diff --git a/Llama3.1-TitanDeluxe-8B-slerp.f16.gguf b/Llama3.1-TitanDeluxe-8B-slerp.f16.gguf new file mode 100644 index 0000000..51ebe70 --- /dev/null +++ b/Llama3.1-TitanDeluxe-8B-slerp.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b56d3a600812d3fde1cc45365333539fe3d7cc0ead97f12ae2fb4a15f5b6d0 +size 16068892384 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5cbb62d --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Stormtrooperaim/Llama3.1-TitanDeluxe-8B-slerp +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- Stormtrooperaim/llama3.1-TitanForge-8B +- Stormtrooperaim/Llama3.1-DeluxeTrifecta-8B +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Stormtrooperaim/Llama3.1-TitanDeluxe-8B-slerp + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-TitanDeluxe-8B-slerp-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-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/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-TitanDeluxe-8B-slerp-GGUF/resolve/main/Llama3.1-TitanDeluxe-8B-slerp.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. + +