commit c5077622b1794d0ef98246ee2597c933ba4a0d11 Author: ModelHub XC Date: Tue Oct 6 12:11:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/vita-llama-3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fe06d13 --- /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 +vita-llama-3-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +vita-llama-3-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ac30c3 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: rpodila/vita-llama-3-8b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/rpodila/vita-llama-3-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#vita-llama-3-8b-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/vita-llama-3-8b-GGUF/resolve/main/vita-llama-3-8b.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. + + diff --git a/vita-llama-3-8b.IQ4_XS.gguf b/vita-llama-3-8b.IQ4_XS.gguf new file mode 100644 index 0000000..aec8ff8 --- /dev/null +++ b/vita-llama-3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b60866dc0caf7a89e331ee108a9253e2f7be531f8be6285056bd0d54cd48aa0 +size 4484363360 diff --git a/vita-llama-3-8b.Q2_K.gguf b/vita-llama-3-8b.Q2_K.gguf new file mode 100644 index 0000000..8ebf8a4 --- /dev/null +++ b/vita-llama-3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878255e7822efc92e052ac9638c6fb65567cf402c8b94b7b6b3b1aefb39530c3 +size 3179132000 diff --git a/vita-llama-3-8b.Q3_K_L.gguf b/vita-llama-3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..2523596 --- /dev/null +++ b/vita-llama-3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce71c9c88cc8f7a350f6a137ad7a098a685432ba6f49d5a22c7fefb2afd62e6 +size 4321956960 diff --git a/vita-llama-3-8b.Q3_K_M.gguf b/vita-llama-3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..ccf0a06 --- /dev/null +++ b/vita-llama-3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83371a68a99bd1912442a11eeb2e96c3c021ae418be12f523a5930780c84658 +size 4018918496 diff --git a/vita-llama-3-8b.Q3_K_S.gguf b/vita-llama-3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..0535a77 --- /dev/null +++ b/vita-llama-3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a453becd3c60c424385bc9b88fd5e5af71c8467d79fd95f799dcdeb3d94bc4 +size 3664499808 diff --git a/vita-llama-3-8b.Q4_K_M.gguf b/vita-llama-3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..f864bbf --- /dev/null +++ b/vita-llama-3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1cedb1b405f807de10dff7261040573d2a780da6eef6498303dc118fd5f039 +size 4920734816 diff --git a/vita-llama-3-8b.Q4_K_S.gguf b/vita-llama-3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..76c6109 --- /dev/null +++ b/vita-llama-3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a6f100533749bd0378fa195eb1b14da972e161c54a0c6368513ebe28691841 +size 4692669536 diff --git a/vita-llama-3-8b.Q5_K_M.gguf b/vita-llama-3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..0ded043 --- /dev/null +++ b/vita-llama-3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0ca7dbe90a550208564a1d5cce96b85c8c38345185a27057f766291411442e +size 5732988000 diff --git a/vita-llama-3-8b.Q5_K_S.gguf b/vita-llama-3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..b0070eb --- /dev/null +++ b/vita-llama-3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8195a2f760e61dd1a8792105f7f07c49a34aee25e818a37a959cdb0cdc37157 +size 5599294560 diff --git a/vita-llama-3-8b.Q6_K.gguf b/vita-llama-3-8b.Q6_K.gguf new file mode 100644 index 0000000..b80e593 --- /dev/null +++ b/vita-llama-3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea650485e9c00b284c890a984343b4d4fabb65511b57ec1c0959d76220cac3cc +size 6596007008 diff --git a/vita-llama-3-8b.Q8_0.gguf b/vita-llama-3-8b.Q8_0.gguf new file mode 100644 index 0000000..87a03f5 --- /dev/null +++ b/vita-llama-3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9290a73d6a46a6f691dd7557ad2cada8c50d0ef476213d0db26cadc9197db3b6 +size 8540771424 diff --git a/vita-llama-3-8b.f16.gguf b/vita-llama-3-8b.f16.gguf new file mode 100644 index 0000000..e2aeba7 --- /dev/null +++ b/vita-llama-3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e88eeb35ffe449657798bba1380347062db7c0a9f3451cbe32ab4fba31eff5f +size 16068891744