commit 1bf6bdb1692bfe58002c265e1d3410a16ac79ed3 Author: ModelHub XC Date: Fri Oct 30 22:56:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3b77332 --- /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 +ArliAI-Llama-3-8B-Dolfin-v0.3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Dolfin-v0.3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_M.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_M.gguf new file mode 100644 index 0000000..68fbbce --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb6e5deda4b5b9f57d6fdb19d8cdc77fcee41a2d2be35552a65a0c30bfcb750 +size 3784823328 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_S.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_S.gguf new file mode 100644 index 0000000..fd5b00e --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64606789e8e6f08d99c680747d8902c35a15fba38f377c97c2bb20b63aab0bee +size 3682325024 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_XS.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_XS.gguf new file mode 100644 index 0000000..0bcc513 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349c07624afe674cf34975fad088c4aee78a3451bfc8edf6f5c81dc677ecadd8 +size 3518747168 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_NL.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_NL.gguf new file mode 100644 index 0000000..cb432c3 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a84881f84c25edbd623199a42a73e67b65ae48c0974e163466d24b9c32b89dbc +size 4707349024 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_XS.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_XS.gguf new file mode 100644 index 0000000..81cfea7 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379703ffc6acd5126e55f0bdeb48115f82a299eb46af4d10f96584430b67a3fb +size 4484362784 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q2_K.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q2_K.gguf new file mode 100644 index 0000000..ffc844a --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8e0eebbc8a0643a8ff6208b45bc2af9d9acec6aad9e6af734eafbb31b84eb28 +size 3179131424 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K.gguf new file mode 100644 index 0000000..2d90e7d --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd369b0bcdffac3e587b6c70a13354b48577e3aae1a97eedebc93a775ca91b5 +size 4018917920 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_L.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_L.gguf new file mode 100644 index 0000000..e09b33b --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193507d3498145a7c59c581ed5be858c8d56be2909b426d9cfa86398fa494774 +size 4321956384 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_M.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_M.gguf new file mode 100644 index 0000000..2d90e7d --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd369b0bcdffac3e587b6c70a13354b48577e3aae1a97eedebc93a775ca91b5 +size 4018917920 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_S.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_S.gguf new file mode 100644 index 0000000..25847f9 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571ec7d87e3c7df3c29171dcb0087946324971149a7cd761e1827e8c0f3fe615 +size 3664499232 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_0.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_0.gguf new file mode 100644 index 0000000..af09805 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9868192729a8c47e4d7d8de9164ecdabf8956ce76b1917b20cd76fbf9070656 +size 4661211680 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_1.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_1.gguf new file mode 100644 index 0000000..38491b9 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a367b80a0ac703d4d8a0c7d557713b65baa05d7acc5ad945f0484bd102fa5a +size 5130252832 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K.gguf new file mode 100644 index 0000000..622e754 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6478e2653104aac242aae9b53ecaf4c47a24c474e3fa3b82c694855af9738e +size 4920734240 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_M.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_M.gguf new file mode 100644 index 0000000..622e754 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6478e2653104aac242aae9b53ecaf4c47a24c474e3fa3b82c694855af9738e +size 4920734240 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_S.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_S.gguf new file mode 100644 index 0000000..c0622a7 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c14104d4807b2e895e4c8249c9acd1137321c6b0d3a7f78626a63a25141174 +size 4692668960 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_0.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_0.gguf new file mode 100644 index 0000000..185db5c --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8146820652ac0a7a3729226dc3d95e0760d558ff6ce427bac3335e7c84e18f48 +size 5599293984 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_1.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_1.gguf new file mode 100644 index 0000000..a627206 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773114e03745a10ea71c9ab838c09033b65bce076f117931b674276001ed2c1c +size 6068335136 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K.gguf new file mode 100644 index 0000000..97f12b9 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5c665b08f504ef6f37dabb21bf5c0586e0e17d82a521b0ffe2f3a28f24cb87 +size 5732987424 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_M.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_M.gguf new file mode 100644 index 0000000..97f12b9 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5c665b08f504ef6f37dabb21bf5c0586e0e17d82a521b0ffe2f3a28f24cb87 +size 5732987424 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_S.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_S.gguf new file mode 100644 index 0000000..cbff8cd --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b410014f59f3ef69b7edde6e632653c04949e89480916fafcf65eaecd1921fc4 +size 5599293984 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q6_K.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q6_K.gguf new file mode 100644 index 0000000..1452593 --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8cde7bf3c3cd070b8e7e4e9e87e24a9ee967aabcd35921471a90668c2bfdd57 +size 6596006432 diff --git a/ArliAI-Llama-3-8B-Dolfin-v0.3.Q8_0.gguf b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q8_0.gguf new file mode 100644 index 0000000..cceb88d --- /dev/null +++ b/ArliAI-Llama-3-8B-Dolfin-v0.3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb2be476630d258f6f1f7a83597f7f8962ea2decfc80fa446c74437debb608c8 +size 8540770848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2b82cd2 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +Quantization made by Richard Erkhov. + +[Github](https://github.com/RichardErkhov) + +[Discord](https://discord.gg/pvy7H8DZMG) + +[Request more models](https://github.com/RichardErkhov/quant_request) + + +ArliAI-Llama-3-8B-Dolfin-v0.3 - GGUF +- Model creator: https://huggingface.co/OwenArli/ +- Original model: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Dolfin-v0.3/ + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q2_K.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q2_K.gguf) | Q2_K | 2.96GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_XS.gguf) | IQ3_XS | 3.28GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_S.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_S.gguf) | IQ3_S | 3.43GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_S.gguf) | Q3_K_S | 3.41GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_M.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ3_M.gguf) | IQ3_M | 3.52GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K.gguf) | Q3_K | 3.74GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_M.gguf) | Q3_K_M | 3.74GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q3_K_L.gguf) | Q3_K_L | 4.03GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_XS.gguf) | IQ4_XS | 4.18GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_0.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_0.gguf) | Q4_0 | 4.34GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.IQ4_NL.gguf) | IQ4_NL | 4.38GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_S.gguf) | Q4_K_S | 4.37GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K.gguf) | Q4_K | 4.58GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_K_M.gguf) | Q4_K_M | 4.58GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_1.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q4_1.gguf) | Q4_1 | 4.78GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_0.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_0.gguf) | Q5_0 | 5.21GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_S.gguf) | Q5_K_S | 5.21GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K.gguf) | Q5_K | 5.34GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_K_M.gguf) | Q5_K_M | 5.34GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_1.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q5_1.gguf) | Q5_1 | 5.65GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q6_K.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q6_K.gguf) | Q6_K | 6.14GB | +| [ArliAI-Llama-3-8B-Dolfin-v0.3.Q8_0.gguf](https://huggingface.co/RichardErkhov/OwenArli_-_ArliAI-Llama-3-8B-Dolfin-v0.3-gguf/blob/main/ArliAI-Llama-3-8B-Dolfin-v0.3.Q8_0.gguf) | Q8_0 | 7.95GB | + + + + +Original model description: +--- +license: llama3 +--- +Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: +https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct + + +This is a fine tune using an improved Dolphin and WizardLM dataset intended to make the model follow instructions better and refuse less. OpenLLM benchmark is running... + + +OpenLLM Benchmark: + + + +Training: +- 2048 sequence length since the dataset has an average length of under 1000 tokens, while the base model is 8192 sequence length. From testing it still performs the same 8192 context just fine. +- Training duration is around 1 days on 2xRTX 3090, using 4-bit loading and Qlora 64-rank 128-alpha resulting in ~2% trainable weights. + + +Instruct format: +``` +<|begin_of_text|><|start_header_id|>system<|end_header_id|> + +{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|> + +{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|> + +{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> +``` + + +Quants: + +FP16: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Dolfin-v0.3 + +GGUF: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Dolfin-v0.3-GGUF + + +