commit 7f56b92c71e89d5b9e2577bf705fc974c3614e69 Author: ModelHub XC Date: Sun Sep 13 00:52:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4e63348 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,64 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-F16.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +EXAONE-3.5-2.4B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EXAONE-3.5-2.4B-Instruct-F16.gguf b/EXAONE-3.5-2.4B-Instruct-F16.gguf new file mode 100644 index 0000000..e9043eb --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca5d64e95185221589f93329820ef791241450d03190c2cabfbc59884279b02 +size 5339453952 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ1_M.gguf b/EXAONE-3.5-2.4B-Instruct-IQ1_M.gguf new file mode 100644 index 0000000..9154cff --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec2d02f0b941d37c806073f8662a3d5ab679bfffb1216fe2d964b3486ac764f6 +size 770448192 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ1_S.gguf b/EXAONE-3.5-2.4B-Instruct-IQ1_S.gguf new file mode 100644 index 0000000..b4468e4 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9019660821424a83a4f3aeb4b77d9ef37eb5c9339f2bc2a9e78ea50c2a914d +size 727271232 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ2_M.gguf b/EXAONE-3.5-2.4B-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..2550cae --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae5e93a7c0965a5c2501667364028a2b5a7db176371b00170dcfd5e3a43c89a +size 1023555392 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ2_S.gguf b/EXAONE-3.5-2.4B-Instruct-IQ2_S.gguf new file mode 100644 index 0000000..bd63ba0 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e260c5241deb73f33ec85227d0cfc81a6b53a941204161b4e87e0b8054183838 +size 965986112 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ2_XS.gguf b/EXAONE-3.5-2.4B-Instruct-IQ2_XS.gguf new file mode 100644 index 0000000..23e8085 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be46f3b26cc840724b52ce0016b208445e2a9145be7634fc9ff4efbaf47b388 +size 906123072 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ2_XXS.gguf b/EXAONE-3.5-2.4B-Instruct-IQ2_XXS.gguf new file mode 100644 index 0000000..d45d1c3 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0d9f9dd31ec0cf7e15561261e04844b56b3b02bb0defe1a2fab607a6a4789a +size 842409792 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ3_M.gguf b/EXAONE-3.5-2.4B-Instruct-IQ3_M.gguf new file mode 100644 index 0000000..142c072 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7744d834f3ec73d44790956976e941b4c02b7ec86b91b085c55793d62c8c060 +size 1293287232 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ3_S.gguf b/EXAONE-3.5-2.4B-Instruct-IQ3_S.gguf new file mode 100644 index 0000000..9da0c6f --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5966ebcc4c5d54774c1e9711e202d8d2516a2565d3709c332ce838e307bec82 +size 1259863872 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ3_XS.gguf b/EXAONE-3.5-2.4B-Instruct-IQ3_XS.gguf new file mode 100644 index 0000000..9aeabd8 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4878fe6005b5765f08d0afe87842fa5ce283be456a6bfa2a208a5aaa32859043 +size 1208776512 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ3_XXS.gguf b/EXAONE-3.5-2.4B-Instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..2b66396 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f6920f9e1aa3d023807b252a89c62f50225a94365c97c1a07af87349260814 +size 1120753472 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ4_NL.gguf b/EXAONE-3.5-2.4B-Instruct-IQ4_NL.gguf new file mode 100644 index 0000000..680cc7a --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f2295b18e8d2ae3fccf2e58a00f1a67509e8b43a06bf1b5edaf6afbf847d661 +size 1578916672 diff --git a/EXAONE-3.5-2.4B-Instruct-IQ4_XS.gguf b/EXAONE-3.5-2.4B-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..86a3b25 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a062e76eef648a02d17140ce7caf9c87f15b0f9f2f323f9559d755fe992a14 +size 1505291072 diff --git a/EXAONE-3.5-2.4B-Instruct-Q2_K.gguf b/EXAONE-3.5-2.4B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..03065c4 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5179cd5c66e8276562bfd162118cb0d7e56388ca2e6105387cb640f36f27bc +size 1096459072 diff --git a/EXAONE-3.5-2.4B-Instruct-Q2_K_S.gguf b/EXAONE-3.5-2.4B-Instruct-Q2_K_S.gguf new file mode 100644 index 0000000..cc3fbb9 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d54926994d35c2432d0cc016fc905dfa44e686125681d2f8de40914958285882 +size 1033483072 diff --git a/EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf b/EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..a230224 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33e32848c16b7cfa6846644279e36950cdc25dd4eda3460ab8c12fc75f85b727 +size 1458622272 diff --git a/EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf b/EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..53d7325 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04358f83cccc9b33ad9adf0047869cdd04a7586cb3de234abea90b532e9b6ea +size 1361792832 diff --git a/EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf b/EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..758de7b --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fb0938dcc6d8bb09dc44790aeca1f1b0c48262cdb33c316574e073161eae26b +size 1253335872 diff --git a/EXAONE-3.5-2.4B-Instruct-Q4_0.gguf b/EXAONE-3.5-2.4B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..454a850 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eac4f4e2147c2c593c49bc5e3b43aba2134083503a24160b0f8837e44b9ebcd0 +size 1576213312 diff --git a/EXAONE-3.5-2.4B-Instruct-Q4_1.gguf b/EXAONE-3.5-2.4B-Instruct-Q4_1.gguf new file mode 100644 index 0000000..bb20d5a --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8cbcb6adefca2b0d2448fc0230387f62a99907a7e559fff1ceb60ed3543104 +size 1723095872 diff --git a/EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf b/EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..370a8d9 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6601a6aa81a3fbe1128d13b836a6c6e17953a6dd84a59b098553e0568496a516 +size 1644918592 diff --git a/EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf b/EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..52a94a5 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a10893d29cdaaca7fdf6e989b1711495bf74da517fa1ed6a08f75415f39456e +size 1580473152 diff --git a/EXAONE-3.5-2.4B-Instruct-Q5_0.gguf b/EXAONE-3.5-2.4B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..ce10f3a --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65aac267675bbcb73f8da78d1548ddf2fbcb5028a64574587bbdbc841f41a6f +size 1876859712 diff --git a/EXAONE-3.5-2.4B-Instruct-Q5_1.gguf b/EXAONE-3.5-2.4B-Instruct-Q5_1.gguf new file mode 100644 index 0000000..531222f --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:774664fd7dd9198421a3215b1307c5e0b777b4b2b72d1bd41cafc3fefc53edb4 +size 2023742272 diff --git a/EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf b/EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..08d7a00 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbac7fd6b5f73594c94d309f1c83c0f34f65d57275a0ff9981dfa2173d000341 +size 1910585152 diff --git a/EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf b/EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..fa305ba --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bedf938beeafc362b0a9e91a30051fc1412d0fdd1c48ece64d45c9e2bb75f013 +size 1873419072 diff --git a/EXAONE-3.5-2.4B-Instruct-Q6_K.gguf b/EXAONE-3.5-2.4B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..bfcf932 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1bacab0fc549aa41e73afeadaa3931fddce63e444cdf541c379d773fc71a23c +size 2192855872 diff --git a/EXAONE-3.5-2.4B-Instruct-Q8_0.gguf b/EXAONE-3.5-2.4B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..99f1c26 --- /dev/null +++ b/EXAONE-3.5-2.4B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e2524424ae8e88888d12eb0be3d927785491ef1901aeed443337f5e0286218 +size 2838846272 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e89d948 --- /dev/null +++ b/README.md @@ -0,0 +1,246 @@ +--- +license: other +license_name: exaone +license_link: LICENSE +language: +- en +- ko +tags: +- lg-ai +- exaone +- exaone-3.5 +pipeline_tag: text-generation +library_name: transformers +--- + +

+ +# Llama.cpp imatrix quantizations of [LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct) + +Using llama.cpp commit [5783575](https://github.com/ggerganov/llama.cpp/commit/5783575) for quantization. + +All quants were made using the imatrix option and Bartowski's [calibration file](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8). + +
+ +# Perplexity table (the lower the better) + +| Quant | Size (MB) | PPL | Size (%) | Accuracy (%) | PPL error rate | +| ------------------------------------------------------------------------------------------------------------------------------ | --------- | ------- | -------- | ------------ | -------------- | +| [IQ1_S](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ1_S.gguf) | 693 | 80.4634 | 13.61 | 12.16 | 1.33 | +| [IQ1_M](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ1_M.gguf) | 734 | 39.7732 | 14.41 | 24.60 | 0.61 | +| [IQ2_XXS](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ2_XXS.gguf) | 803 | 20.3081 | 15.77 | 48.18 | 0.30 | +| [IQ2_XS](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ2_XS.gguf) | 864 | 15.7232 | 16.97 | 62.23 | 0.23 | +| [IQ2_S](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ2_S.gguf) | 921 | 14.1473 | 18.09 | 69.16 | 0.21 | +| [IQ2_M](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ2_M.gguf) | 976 | 12.5527 | 19.17 | 77.95 | 0.18 | +| [Q2_K_S](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q2_K_S.gguf) | 985 | 13.7018 | 19.34 | 71.41 | 0.20 | +| [Q2_K](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q2_K.gguf) | 1045 | 12.5399 | 20.52 | 78.03 | 0.19 | +| [IQ3_XXS](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ3_XXS.gguf) | 1068 | 11.1884 | 20.97 | 87.45 | 0.16 | +| [IQ3_XS](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ3_XS.gguf) | 1152 | 10.8551 | 22.62 | 90.14 | 0.16 | +| [Q3_K_S](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf) | 1195 | 11.0653 | 23.47 | 88.43 | 0.16 | +| [IQ3_S](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ3_S.gguf) | 1201 | 10.6916 | 23.59 | 91.51 | 0.15 | +| [IQ3_M](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ3_M.gguf) | 1233 | 10.6124 | 24.21 | 92.20 | 0.15 | +| [Q3_K_M](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf) | 1298 | 10.3392 | 25.49 | 94.63 | 0.15 | +| [Q3_K_L](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf) | 1391 | 10.2274 | 27.32 | 95.67 | 0.15 | +| [IQ4_XS](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ4_XS.gguf) | 1435 | 10.0262 | 28.18 | 97.59 | 0.15 | +| [Q4_0](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q4_0.gguf) | 1503 | 10.1964 | 29.52 | 95.96 | 0.15 | +| [IQ4_NL](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-IQ4_NL.gguf) | 1505 | 9.9962 | 29.56 | 97.88 | 0.15 | +| [Q4_K_S](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf) | 1507 | 10.0445 | 29.59 | 97.41 | 0.15 | +| [Q4_K_M](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf) | 1568 | 10.0122 | 30.79 | 97.72 | 0.15 | +| [Q4_1](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q4_1.gguf) | 1643 | 10.0464 | 32.27 | 97.39 | 0.15 | +| [Q5_K_S](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf) | 1786 | 9.8232 | 35.07 | 99.61 | 0.14 | +| [Q5_0](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q5_0.gguf) | 1789 | 9.8700 | 35.13 | 99.13 | 0.14 | +| [Q5_K_M](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf) | 1822 | 9.8565 | 35.78 | 99.27 | 0.14 | +| [Q5_1](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q5_1.gguf) | 1929 | 9.8203 | 37.88 | 99.64 | 0.14 | +| [Q6_K](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q6_K.gguf) | 2091 | 9.8229 | 41.06 | 99.61 | 0.14 | +| [Q8_0](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-Q8_0.gguf) | 2707 | 9.7928 | 53.16 | 99.92 | 0.14 | +| [F16](https://huggingface.co/ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-GGUF/blob/main/EXAONE-3.5-2.4B-Instruct-F16.gguf) | 5092 | 9.7845 | 100 | 100 | 0.14 | + +
+ +

+ +
+ +# EXAONE-3.5-2.4B-Instruct + +## Introduction + +We introduce EXAONE 3.5, a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research. EXAONE 3.5 language models include: 1) **2.4B model** optimized for deployment on small or resource-constrained devices, 2) **7.8B model** matching the size of its predecessor but offering improved performance, and 3) **32B model** delivering powerful performance. All models support long-context processing of up to 32K tokens. Each model demonstrates state-of-the-art performance in real-world use cases and long-context understanding, while remaining competitive in general domains compared to recently released models of similar sizes. + +For more details, please refer to our [technical report](https://arxiv.org/abs/2412.04862), [blog](https://www.lgresearch.ai/blog/view?seq=507) and [GitHub](https://github.com/LG-AI-EXAONE/EXAONE-3.5). + +This repository contains the instruction-tuned 2.4B language model with the following features: + +- Number of Parameters (without embeddings): 2.14B +- Number of Layers: 30 +- Number of Attention Heads: GQA with 32 Q-heads and 8 KV-heads +- Vocab Size: 102,400 +- Context Length: 32,768 tokens +- Tie Word Embeddings: True (unlike 7.8B and 32B models) + +## Quickstart + +We recommend to use `transformers` v4.43 or later. + +Here is the code snippet to run conversational inference with the model: + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct" + +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype=torch.bfloat16, + trust_remote_code=True, + device_map="auto" +) +tokenizer = AutoTokenizer.from_pretrained(model_name) + +# Choose your prompt +prompt = "Explain how wonderful you are" # English example +prompt = "스스로를 자랑해 봐" # Korean example + +messages = [ + {"role": "system", + "content": "You are EXAONE model from LG AI Research, a helpful assistant."}, + {"role": "user", "content": prompt} +] +input_ids = tokenizer.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_tensors="pt" +) + +output = model.generate( + input_ids.to("cuda"), + eos_token_id=tokenizer.eos_token_id, + max_new_tokens=128, + do_sample=False, +) +print(tokenizer.decode(output[0])) +``` + +> ### Note +> The EXAONE 3.5 instruction-tuned language models were trained to utilize the system prompt, +> so we highly recommend using the system prompts provided in the code snippet above. + +## Evaluation + +The following table shows the evaluation results of real-world use cases. The full evaluation results can be found in the [technical report](https://arxiv.org/abs/2412.04862). + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelsMT-BenchLiveBenchArena-HardAlpacaEvalIFEvalKoMT-Bench[1]LogicKor
EXAONE 3.5 2.4B7.8133.048.237.173.67.248.51
Qwen 2.5 3B7.2125.726.417.460.85.685.21
Qwen 2.5 1.5B5.7219.210.68.440.73.873.60
Llama 3.2 3B6.9424.014.218.770.13.162.86
Gemma 2 2B7.2020.019.129.150.54.835.29
+ +- [1] KoMT-Bench is a dataset created by translating MT-Bench into Korean; see [README](https://github.com/LG-AI-EXAONE/KoMT-Bench) for more details. + +## Deployment + +EXAONE 3.5 models can be inferred in the various frameworks, such as: +- `TensorRT-LLM` +- `vLLM` +- `SGLang` +- `llama.cpp` +- `Ollama` + +Please refer to our [EXAONE 3.5 GitHub](https://github.com/LG-AI-EXAONE/EXAONE-3.5) for more details about the inference frameworks. + +## Quantization + +We provide the pre-quantized EXAONE 3.5 models with **AWQ** and several quantization types in **GGUF** format. +Please refer to our [EXAONE 3.5 collection](https://huggingface.co/collections/LGAI-EXAONE/exaone-35-674d0e1bb3dcd2ab6f39dbb4) to find corresponding quantized models. + +## Limitation + +The EXAONE language model has certain limitations and may occasionally generate inappropriate responses. The language model generates responses based on the output probability of tokens, and it is determined during learning from training data. While we have made every effort to exclude personal, harmful, and biased information from the training data, some problematic content may still be included, potentially leading to undesirable responses. Please note that the text generated by EXAONE language model does not reflects the views of LG AI Research. + +- Inappropriate answers may be generated, which contain personal, harmful or other inappropriate information. +- Biased responses may be generated, which are associated with age, gender, race, and so on. +- The generated responses rely heavily on statistics from the training data, which can result in the generation of +semantically or syntactically incorrect sentences. +- Since the model does not reflect the latest information, the responses may be false or contradictory. + +LG AI Research strives to reduce potential risks that may arise from EXAONE language models. Users are not allowed +to engage in any malicious activities (e.g., keying in illegal information) that may induce the creation of inappropriate +outputs violating LG AI’s ethical principles when using EXAONE language models. + +## License + +The model is licensed under [EXAONE AI Model License Agreement 1.1 - NC](./LICENSE) + +## Citation + +``` +@article{exaone-3.5, + title={EXAONE 3.5: Series of Large Language Models for Real-world Use Cases}, + author={LG AI Research}, + journal={arXiv preprint arXiv:https://arxiv.org/abs/2412.04862}, + year={2024} +} +``` + +## Contact +LG AI Research Technical Support: contact_us@lgresearch.ai \ No newline at end of file diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..ea15d2a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b849a35401e6b3df48548d52e9e9d50607bfdc907f81f192fbdfc9cc280f685 +size 2710346 diff --git a/perplexity.md b/perplexity.md new file mode 100644 index 0000000..b7b4f48 --- /dev/null +++ b/perplexity.md @@ -0,0 +1,30 @@ +| Quant | Size (MB) | PPL | Size (%) | Accuracy (%) | PPL error rate | +| ------ | --------- | ------- | -------- | ------------ | -------------- | +| IQ1_S | 693 | 80.4634 | 13.61 | 12.16 | 1.33 | +| IQ1_M | 734 | 39.7732 | 14.41 | 24.60 | 0.61 | +| IQ2_XXS | 803 | 20.3081 | 15.77 | 48.18 | 0.30 | +| IQ2_XS | 864 | 15.7232 | 16.97 | 62.23 | 0.23 | +| IQ2_S | 921 | 14.1473 | 18.09 | 69.16 | 0.21 | +| IQ2_M | 976 | 12.5527 | 19.17 | 77.95 | 0.18 | +| Q2_K_S | 985 | 13.7018 | 19.34 | 71.41 | 0.20 | +| Q2_K | 1045 | 12.5399 | 20.52 | 78.03 | 0.19 | +| IQ3_XXS | 1068 | 11.1884 | 20.97 | 87.45 | 0.16 | +| IQ3_XS | 1152 | 10.8551 | 22.62 | 90.14 | 0.16 | +| Q3_K_S | 1195 | 11.0653 | 23.47 | 88.43 | 0.16 | +| IQ3_S | 1201 | 10.6916 | 23.59 | 91.51 | 0.15 | +| IQ3_M | 1233 | 10.6124 | 24.21 | 92.20 | 0.15 | +| Q3_K_M | 1298 | 10.3392 | 25.49 | 94.63 | 0.15 | +| Q3_K_L | 1391 | 10.2274 | 27.32 | 95.67 | 0.15 | +| IQ4_XS | 1435 | 10.0262 | 28.18 | 97.59 | 0.15 | +| Q4_0 | 1503 | 10.1964 | 29.52 | 95.96 | 0.15 | +| IQ4_NL | 1505 | 9.9962 | 29.56 | 97.88 | 0.15 | +| Q4_K_S | 1507 | 10.0445 | 29.59 | 97.41 | 0.15 | +| Q4_K_M | 1568 | 10.0122 | 30.79 | 97.72 | 0.15 | +| Q4_1 | 1643 | 10.0464 | 32.27 | 97.39 | 0.15 | +| Q5_K_S | 1786 | 9.8232 | 35.07 | 99.61 | 0.14 | +| Q5_0 | 1789 | 9.8700 | 35.13 | 99.13 | 0.14 | +| Q5_K_M | 1822 | 9.8565 | 35.78 | 99.27 | 0.14 | +| Q5_1 | 1929 | 9.8203 | 37.88 | 99.64 | 0.14 | +| Q6_K | 2091 | 9.8229 | 41.06 | 99.61 | 0.14 | +| Q8_0 | 2707 | 9.7928 | 53.16 | 99.92 | 0.14 | +| F16 | 5092 | 9.7845 | 100 | 100 | 0.14 |