commit b096438cd3f96467fdaf9a6dd12fe49ecd7f79f0 Author: ModelHub XC Date: Wed Jun 3 23:50:40 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RichardErkhov/Diksha2001_-_VLLM-new-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1053506 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +VLLM-new.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +VLLM-new.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9d46a90 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +Quantization made by Richard Erkhov. + +[Github](https://github.com/RichardErkhov) + +[Discord](https://discord.gg/pvy7H8DZMG) + +[Request more models](https://github.com/RichardErkhov/quant_request) + + +VLLM-new - GGUF +- Model creator: https://huggingface.co/Diksha2001/ +- Original model: https://huggingface.co/Diksha2001/VLLM-new/ + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [VLLM-new.Q2_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q2_K.gguf) | Q2_K | 2.96GB | +| [VLLM-new.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ3_XS.gguf) | IQ3_XS | 3.28GB | +| [VLLM-new.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ3_S.gguf) | IQ3_S | 3.43GB | +| [VLLM-new.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q3_K_S.gguf) | Q3_K_S | 3.41GB | +| [VLLM-new.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ3_M.gguf) | IQ3_M | 3.52GB | +| [VLLM-new.Q3_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q3_K.gguf) | Q3_K | 3.74GB | +| [VLLM-new.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q3_K_M.gguf) | Q3_K_M | 3.74GB | +| [VLLM-new.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q3_K_L.gguf) | Q3_K_L | 4.03GB | +| [VLLM-new.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ4_XS.gguf) | IQ4_XS | 4.18GB | +| [VLLM-new.Q4_0.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_0.gguf) | Q4_0 | 4.34GB | +| [VLLM-new.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.IQ4_NL.gguf) | IQ4_NL | 4.38GB | +| [VLLM-new.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_K_S.gguf) | Q4_K_S | 4.37GB | +| [VLLM-new.Q4_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_K.gguf) | Q4_K | 4.58GB | +| [VLLM-new.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_K_M.gguf) | Q4_K_M | 4.58GB | +| [VLLM-new.Q4_1.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q4_1.gguf) | Q4_1 | 4.78GB | +| [VLLM-new.Q5_0.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_0.gguf) | Q5_0 | 5.21GB | +| [VLLM-new.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_K_S.gguf) | Q5_K_S | 5.21GB | +| [VLLM-new.Q5_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_K.gguf) | Q5_K | 5.34GB | +| [VLLM-new.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_K_M.gguf) | Q5_K_M | 5.34GB | +| [VLLM-new.Q5_1.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q5_1.gguf) | Q5_1 | 5.65GB | +| [VLLM-new.Q6_K.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q6_K.gguf) | Q6_K | 6.14GB | +| [VLLM-new.Q8_0.gguf](https://huggingface.co/RichardErkhov/Diksha2001_-_VLLM-new-gguf/blob/main/VLLM-new.Q8_0.gguf) | Q8_0 | 7.95GB | + + + + +Original model description: +--- +base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +license: apache-2.0 +language: +- en +--- + +# Uploaded model + +- **Developed by:** Diksha2001 +- **License:** apache-2.0 +- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-bnb-4bit + +This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. + +[](https://github.com/unslothai/unsloth) + + diff --git a/VLLM-new.IQ3_M.gguf b/VLLM-new.IQ3_M.gguf new file mode 100644 index 0000000..3144989 --- /dev/null +++ b/VLLM-new.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86873f9080eb68cd7dba52612680389735b2bd114b1d7e642ab7481a1894c94c +size 3784824736 diff --git a/VLLM-new.IQ3_S.gguf b/VLLM-new.IQ3_S.gguf new file mode 100644 index 0000000..c2608fd --- /dev/null +++ b/VLLM-new.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c6f295f0203d30f748cfa87c7d3221059c4d2572e1e6c4c2b77fb990ecfe0b4 +size 3682326432 diff --git a/VLLM-new.IQ3_XS.gguf b/VLLM-new.IQ3_XS.gguf new file mode 100644 index 0000000..1ca532b --- /dev/null +++ b/VLLM-new.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0648f2dec952f2cdfcc50691147958d4b0392349f42046e1cd5ca4e5a4d73f18 +size 3518748576 diff --git a/VLLM-new.IQ4_NL.gguf b/VLLM-new.IQ4_NL.gguf new file mode 100644 index 0000000..4db7bd8 --- /dev/null +++ b/VLLM-new.IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5271124a53abcf711389b49cfc0c5081cdc67f5e07b546b92ff4890670ba1756 +size 4707350432 diff --git a/VLLM-new.IQ4_XS.gguf b/VLLM-new.IQ4_XS.gguf new file mode 100644 index 0000000..354d773 --- /dev/null +++ b/VLLM-new.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d14dc6decc5abee4ccfb88a87fd48db2b3a5fe11d7e71f69a3dea2ec46de858 +size 4484364192 diff --git a/VLLM-new.Q2_K.gguf b/VLLM-new.Q2_K.gguf new file mode 100644 index 0000000..76446ed --- /dev/null +++ b/VLLM-new.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99ecac93f8e2ce454a20d6b275a46b90f645eb2067a0690e4b4bc7eadbba2aa6 +size 3179132832 diff --git a/VLLM-new.Q3_K.gguf b/VLLM-new.Q3_K.gguf new file mode 100644 index 0000000..016f2da --- /dev/null +++ b/VLLM-new.Q3_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8238bfb010b346da2b42f33b15cf7e661aef1f4a997894138fd503d2f079342 +size 4018919328 diff --git a/VLLM-new.Q3_K_L.gguf b/VLLM-new.Q3_K_L.gguf new file mode 100644 index 0000000..3519183 --- /dev/null +++ b/VLLM-new.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8411f83551f82774bd2f23b60452d5a291fc04d65ab0d847f5cf7969bfd70c54 +size 4321957792 diff --git a/VLLM-new.Q3_K_M.gguf b/VLLM-new.Q3_K_M.gguf new file mode 100644 index 0000000..016f2da --- /dev/null +++ b/VLLM-new.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8238bfb010b346da2b42f33b15cf7e661aef1f4a997894138fd503d2f079342 +size 4018919328 diff --git a/VLLM-new.Q3_K_S.gguf b/VLLM-new.Q3_K_S.gguf new file mode 100644 index 0000000..700be41 --- /dev/null +++ b/VLLM-new.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f981ce3965c35a33444ae28f0365d5d065bf17ef73dbfd710a5d21637a43835 +size 3664500640 diff --git a/VLLM-new.Q4_0.gguf b/VLLM-new.Q4_0.gguf new file mode 100644 index 0000000..5ed3559 --- /dev/null +++ b/VLLM-new.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71ef9a0852a2ff2a52b223b48744362e897c760070372eadb2c9733d0922dc7c +size 4661213088 diff --git a/VLLM-new.Q4_1.gguf b/VLLM-new.Q4_1.gguf new file mode 100644 index 0000000..843db39 --- /dev/null +++ b/VLLM-new.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e123410969466277d5f9cc5c1d94f8ca6c36166c43c94154f010836d4aba90 +size 5130254240 diff --git a/VLLM-new.Q4_K.gguf b/VLLM-new.Q4_K.gguf new file mode 100644 index 0000000..794cc81 --- /dev/null +++ b/VLLM-new.Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6688dc288227b8f715aabb2dec6dbbb3932c501c083d6405d1dc65a0777d72a +size 4920735648 diff --git a/VLLM-new.Q4_K_M.gguf b/VLLM-new.Q4_K_M.gguf new file mode 100644 index 0000000..794cc81 --- /dev/null +++ b/VLLM-new.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6688dc288227b8f715aabb2dec6dbbb3932c501c083d6405d1dc65a0777d72a +size 4920735648 diff --git a/VLLM-new.Q4_K_S.gguf b/VLLM-new.Q4_K_S.gguf new file mode 100644 index 0000000..284e1de --- /dev/null +++ b/VLLM-new.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3b8f6faec5292e69d28fd90da62457ba9136db68243e71e9afcce5e307c0af +size 4692670368 diff --git a/VLLM-new.Q5_0.gguf b/VLLM-new.Q5_0.gguf new file mode 100644 index 0000000..365fd8d --- /dev/null +++ b/VLLM-new.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce13ba136786316b9d53dfc31c0424db7fc1751d78269d6dca6587f2c2900d04 +size 5599295392 diff --git a/VLLM-new.Q5_1.gguf b/VLLM-new.Q5_1.gguf new file mode 100644 index 0000000..1bf97f6 --- /dev/null +++ b/VLLM-new.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3190d93c96e6cb8b96a87db9b882e5f57c8842d882198a89c12e4aa0f6f6504e +size 6068336544 diff --git a/VLLM-new.Q5_K.gguf b/VLLM-new.Q5_K.gguf new file mode 100644 index 0000000..ec6597c --- /dev/null +++ b/VLLM-new.Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f2d04be386483acf6635c71d7a483c961eccbf7020999e0138ecd11a9fea7fe +size 5732988832 diff --git a/VLLM-new.Q5_K_M.gguf b/VLLM-new.Q5_K_M.gguf new file mode 100644 index 0000000..ec6597c --- /dev/null +++ b/VLLM-new.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f2d04be386483acf6635c71d7a483c961eccbf7020999e0138ecd11a9fea7fe +size 5732988832 diff --git a/VLLM-new.Q5_K_S.gguf b/VLLM-new.Q5_K_S.gguf new file mode 100644 index 0000000..3e5111f --- /dev/null +++ b/VLLM-new.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db604468376e0bf9ad76274ddf87363bf844877be6e2e187ae7f039d49e80ab +size 5599295392 diff --git a/VLLM-new.Q6_K.gguf b/VLLM-new.Q6_K.gguf new file mode 100644 index 0000000..4f7acd7 --- /dev/null +++ b/VLLM-new.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c5b11ffa9704d393a6fb10f48b4169d13bc10e4171c5466f5d8ef390793b95 +size 6596007840 diff --git a/VLLM-new.Q8_0.gguf b/VLLM-new.Q8_0.gguf new file mode 100644 index 0000000..790e624 --- /dev/null +++ b/VLLM-new.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87067662ecdf9d5806555494f7b7ea0a02433aadfef6c053aa8be1437d487522 +size 8540772256