commit fab6a41fe5532fe863df71c32721f34ee2ee91de Author: ModelHub XC Date: Mon Sep 21 13:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-VNTL-Vectors-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..77d6eca --- /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 +Llama-3-VNTL-Vectors.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-VNTL-Vectors.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-VNTL-Vectors.IQ4_XS.gguf b/Llama-3-VNTL-Vectors.IQ4_XS.gguf new file mode 100644 index 0000000..4e371e8 --- /dev/null +++ b/Llama-3-VNTL-Vectors.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3370e93dd233b490c92985058ee953c4ae543ce77496e8c35aab162cb3bd8caf +size 4484364256 diff --git a/Llama-3-VNTL-Vectors.Q2_K.gguf b/Llama-3-VNTL-Vectors.Q2_K.gguf new file mode 100644 index 0000000..616200d --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55dbd2f08352b9be85ba941de20efb282049430e970ed4f17ce4aede67e85291 +size 3179132896 diff --git a/Llama-3-VNTL-Vectors.Q3_K_L.gguf b/Llama-3-VNTL-Vectors.Q3_K_L.gguf new file mode 100644 index 0000000..6a463bb --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75f4642dc8c21707858c2b4d8b4931bc94912e74e19e7b38123def8efdda6a23 +size 4321957856 diff --git a/Llama-3-VNTL-Vectors.Q3_K_M.gguf b/Llama-3-VNTL-Vectors.Q3_K_M.gguf new file mode 100644 index 0000000..9e4d4e7 --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85ea29bc2dbf4cdb4371fba80a73224be49cf9523c100209d810b3dcf225454c +size 4018919392 diff --git a/Llama-3-VNTL-Vectors.Q3_K_S.gguf b/Llama-3-VNTL-Vectors.Q3_K_S.gguf new file mode 100644 index 0000000..092c888 --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9622efe190c74ae7db4005dea73ba7a51fecb7f4c02122fd812e9695c76200fe +size 3664500704 diff --git a/Llama-3-VNTL-Vectors.Q4_K_M.gguf b/Llama-3-VNTL-Vectors.Q4_K_M.gguf new file mode 100644 index 0000000..14e166a --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d50f4ba57507005b71d1118533058d6a0b675861c228ef5d422b7523481a1989 +size 4920735712 diff --git a/Llama-3-VNTL-Vectors.Q4_K_S.gguf b/Llama-3-VNTL-Vectors.Q4_K_S.gguf new file mode 100644 index 0000000..bf0aab9 --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9a1220ad8987f9fa0c681a8fb2397220391e4051c2ec29b8f0f41b4bd7b2ee2 +size 4692670432 diff --git a/Llama-3-VNTL-Vectors.Q5_K_M.gguf b/Llama-3-VNTL-Vectors.Q5_K_M.gguf new file mode 100644 index 0000000..daa9fd9 --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3d6dc85d9afdc523d5197169f6ff7b7ce1046c0a9dbd0c0ff6d75e13283131 +size 5732988896 diff --git a/Llama-3-VNTL-Vectors.Q5_K_S.gguf b/Llama-3-VNTL-Vectors.Q5_K_S.gguf new file mode 100644 index 0000000..7f6f05c --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ebd1c557c533598af0f7fbc7fc6b76613a2242088621849e9389c09f1bd418 +size 5599295456 diff --git a/Llama-3-VNTL-Vectors.Q6_K.gguf b/Llama-3-VNTL-Vectors.Q6_K.gguf new file mode 100644 index 0000000..7338462 --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b025988fcdd3b5ad720b44f0c1a8803f199a7b65fbb3d07a2bd779d3ce60ff +size 6596007904 diff --git a/Llama-3-VNTL-Vectors.Q8_0.gguf b/Llama-3-VNTL-Vectors.Q8_0.gguf new file mode 100644 index 0000000..bbd8dfc --- /dev/null +++ b/Llama-3-VNTL-Vectors.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ec6f15d5179f5c8c256936f9b02fbfa81b0b34fe4bae68d6acf16373ca68dd +size 8540772320 diff --git a/Llama-3-VNTL-Vectors.f16.gguf b/Llama-3-VNTL-Vectors.f16.gguf new file mode 100644 index 0000000..eacd50c --- /dev/null +++ b/Llama-3-VNTL-Vectors.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b91e8887a18a1ca5a5f978f70be7e4856eeb271779e8ad368fb6fcca69afbedb +size 16068892640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eb56721 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Cas-Warehouse/Llama-3-VNTL-Vectors +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Cas-Warehouse/Llama-3-VNTL-Vectors + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-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/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-VNTL-Vectors-GGUF/resolve/main/Llama-3-VNTL-Vectors.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. + +