commit 9cb6e934b083a3ee9ba7a16988ba4d9584e2424c Author: ModelHub XC Date: Thu Jun 4 04:10:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6f1595b --- /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 +OLMoE-1B-7B-0924-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0924-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMoE-1B-7B-0924-Instruct.IQ3_M.gguf b/OLMoE-1B-7B-0924-Instruct.IQ3_M.gguf new file mode 100644 index 0000000..7100140 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c5dc5047bb4c1918f98586e836e4ff7e6e2940bcd412c3de6e44e4b614b589a +size 3076543008 diff --git a/OLMoE-1B-7B-0924-Instruct.IQ3_S.gguf b/OLMoE-1B-7B-0924-Instruct.IQ3_S.gguf new file mode 100644 index 0000000..89a3289 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89b97c831d34972aa529204ece989da7e07b4d7a82b631e05812faa0dd2900b7 +size 3023065632 diff --git a/OLMoE-1B-7B-0924-Instruct.IQ3_XS.gguf b/OLMoE-1B-7B-0924-Instruct.IQ3_XS.gguf new file mode 100644 index 0000000..4ab6590 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:343793bac4f673aa04d682eaa118df12f9a940f4e25171da9c0ba2ae8493c6dc +size 2865779232 diff --git a/OLMoE-1B-7B-0924-Instruct.IQ4_NL.gguf b/OLMoE-1B-7B-0924-Instruct.IQ4_NL.gguf new file mode 100644 index 0000000..3446848 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffc04ca0f270bd2107ee27b11ac72fc159d3229399da50044031e410ad2b193 +size 3961592352 diff --git a/OLMoE-1B-7B-0924-Instruct.IQ4_XS.gguf b/OLMoE-1B-7B-0924-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..968b554 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a70decf4a2f15ba103b3695d9b2946ce2c6e323251bf420a0eb6f90ea77d9f8 +size 3757046304 diff --git a/OLMoE-1B-7B-0924-Instruct.Q2_K.gguf b/OLMoE-1B-7B-0924-Instruct.Q2_K.gguf new file mode 100644 index 0000000..d10b4d0 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00615d4bfaa7b3953d331224191beda8f233debc7c86682c04903c9ff7cea424 +size 2562763296 diff --git a/OLMoE-1B-7B-0924-Instruct.Q3_K.gguf b/OLMoE-1B-7B-0924-Instruct.Q3_K.gguf new file mode 100644 index 0000000..b4fb746 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q3_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafa6b3e5cff5bbf2bf0424cfb47fd6d9d921df9aa370f9b4bbbbd1a2d943203 +size 3343929888 diff --git a/OLMoE-1B-7B-0924-Instruct.Q3_K_L.gguf b/OLMoE-1B-7B-0924-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c8c6f4e --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce91c53694c99ef6a38b5f58b92b5a0db4c76f982d2fc75f98386fe3e04bfbbf +size 3611316768 diff --git a/OLMoE-1B-7B-0924-Instruct.Q3_K_M.gguf b/OLMoE-1B-7B-0924-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b4fb746 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafa6b3e5cff5bbf2bf0424cfb47fd6d9d921df9aa370f9b4bbbbd1a2d943203 +size 3343929888 diff --git a/OLMoE-1B-7B-0924-Instruct.Q3_K_S.gguf b/OLMoE-1B-7B-0924-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..9c039e8 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19b7d6e6fffa18c1841e26976000da4a72676b9111f6d8abf894d86cfbedc49 +size 3023065632 diff --git a/OLMoE-1B-7B-0924-Instruct.Q4_0.gguf b/OLMoE-1B-7B-0924-Instruct.Q4_0.gguf new file mode 100644 index 0000000..e27951e --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47862e9bb94b3d2e41bbb5b37b23560acac6fe06e7ca1f4dcaabbaefee2c35c +size 3928037920 diff --git a/OLMoE-1B-7B-0924-Instruct.Q4_1.gguf b/OLMoE-1B-7B-0924-Instruct.Q4_1.gguf new file mode 100644 index 0000000..8be3abf --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0ce217b826c4b1236a6e6ea0e0eb98b185bed3e40e043b14cd3795e3283532 +size 4353907232 diff --git a/OLMoE-1B-7B-0924-Instruct.Q4_K.gguf b/OLMoE-1B-7B-0924-Instruct.Q4_K.gguf new file mode 100644 index 0000000..191b69f --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc802c4643aa039d7bb8ed4235045290f83271cbbd86e3535be073e0e833116 +size 4213512736 diff --git a/OLMoE-1B-7B-0924-Instruct.Q4_K_M.gguf b/OLMoE-1B-7B-0924-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..191b69f --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc802c4643aa039d7bb8ed4235045290f83271cbbd86e3535be073e0e833116 +size 4213512736 diff --git a/OLMoE-1B-7B-0924-Instruct.Q4_K_S.gguf b/OLMoE-1B-7B-0924-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..e1daf5a --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1036f3533e6fe9f9c6692719d4ccb7dc5c0c8b79b050c475f66dd03a13d4a0e +size 3963689504 diff --git a/OLMoE-1B-7B-0924-Instruct.Q5_0.gguf b/OLMoE-1B-7B-0924-Instruct.Q5_0.gguf new file mode 100644 index 0000000..aee50f5 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e5a14a6c629ec40cbc0ec83bc8e52a78717a63364a46521e5506eb1b62531c +size 4779776544 diff --git a/OLMoE-1B-7B-0924-Instruct.Q5_1.gguf b/OLMoE-1B-7B-0924-Instruct.Q5_1.gguf new file mode 100644 index 0000000..3a8d4f6 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9c3645defc5e50ab435d0463d56b14ef90f6f99a7d27baf69531430389e93d1 +size 5205645856 diff --git a/OLMoE-1B-7B-0924-Instruct.Q5_K.gguf b/OLMoE-1B-7B-0924-Instruct.Q5_K.gguf new file mode 100644 index 0000000..4d315e5 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454b257371b8fe56d3644a09eedb5e1d565421edf106a8a229c98c3d7d32a419 +size 4926839328 diff --git a/OLMoE-1B-7B-0924-Instruct.Q5_K_M.gguf b/OLMoE-1B-7B-0924-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..4d315e5 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454b257371b8fe56d3644a09eedb5e1d565421edf106a8a229c98c3d7d32a419 +size 4926839328 diff --git a/OLMoE-1B-7B-0924-Instruct.Q5_K_S.gguf b/OLMoE-1B-7B-0924-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..a4f1347 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b98be07a6657f351678f7c9cacbccdb160820afa05056f78c984c9a64ca1a56 +size 4779776544 diff --git a/OLMoE-1B-7B-0924-Instruct.Q6_K.gguf b/OLMoE-1B-7B-0924-Instruct.Q6_K.gguf new file mode 100644 index 0000000..ab88027 --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3523bfb51929e78ad569c6c064eb053b6513b32878e9962c9f0e34329c4e6132 +size 5684748832 diff --git a/OLMoE-1B-7B-0924-Instruct.Q8_0.gguf b/OLMoE-1B-7B-0924-Instruct.Q8_0.gguf new file mode 100644 index 0000000..6e6cd5b --- /dev/null +++ b/OLMoE-1B-7B-0924-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb64524c417c93d374380d3e82f85c3a9b41667cbc98608b984b9ef4d1cd513 +size 7359943200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..05f6de9 --- /dev/null +++ b/README.md @@ -0,0 +1,140 @@ +Quantization made by Richard Erkhov. + +[Github](https://github.com/RichardErkhov) + +[Discord](https://discord.gg/pvy7H8DZMG) + +[Request more models](https://github.com/RichardErkhov/quant_request) + + +OLMoE-1B-7B-0924-Instruct - GGUF +- Model creator: https://huggingface.co/allenai/ +- Original model: https://huggingface.co/allenai/OLMoE-1B-7B-0924-Instruct/ + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [OLMoE-1B-7B-0924-Instruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q2_K.gguf) | Q2_K | 2.39GB | +| [OLMoE-1B-7B-0924-Instruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.IQ3_XS.gguf) | IQ3_XS | 2.67GB | +| [OLMoE-1B-7B-0924-Instruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.IQ3_S.gguf) | IQ3_S | 2.82GB | +| [OLMoE-1B-7B-0924-Instruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q3_K_S.gguf) | Q3_K_S | 2.82GB | +| [OLMoE-1B-7B-0924-Instruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.IQ3_M.gguf) | IQ3_M | 2.87GB | +| [OLMoE-1B-7B-0924-Instruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q3_K.gguf) | Q3_K | 3.11GB | +| [OLMoE-1B-7B-0924-Instruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.11GB | +| [OLMoE-1B-7B-0924-Instruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.36GB | +| [OLMoE-1B-7B-0924-Instruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.IQ4_XS.gguf) | IQ4_XS | 3.5GB | +| [OLMoE-1B-7B-0924-Instruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q4_0.gguf) | Q4_0 | 3.66GB | +| [OLMoE-1B-7B-0924-Instruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.IQ4_NL.gguf) | IQ4_NL | 3.69GB | +| [OLMoE-1B-7B-0924-Instruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q4_K_S.gguf) | Q4_K_S | 3.69GB | +| [OLMoE-1B-7B-0924-Instruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q4_K.gguf) | Q4_K | 3.92GB | +| [OLMoE-1B-7B-0924-Instruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q4_K_M.gguf) | Q4_K_M | 3.92GB | +| [OLMoE-1B-7B-0924-Instruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q4_1.gguf) | Q4_1 | 4.05GB | +| [OLMoE-1B-7B-0924-Instruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q5_0.gguf) | Q5_0 | 4.45GB | +| [OLMoE-1B-7B-0924-Instruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q5_K_S.gguf) | Q5_K_S | 4.45GB | +| [OLMoE-1B-7B-0924-Instruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q5_K.gguf) | Q5_K | 4.59GB | +| [OLMoE-1B-7B-0924-Instruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q5_K_M.gguf) | Q5_K_M | 4.59GB | +| [OLMoE-1B-7B-0924-Instruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q5_1.gguf) | Q5_1 | 4.85GB | +| [OLMoE-1B-7B-0924-Instruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q6_K.gguf) | Q6_K | 5.29GB | +| [OLMoE-1B-7B-0924-Instruct.Q8_0.gguf](https://huggingface.co/RichardErkhov/allenai_-_OLMoE-1B-7B-0924-Instruct-gguf/blob/main/OLMoE-1B-7B-0924-Instruct.Q8_0.gguf) | Q8_0 | 6.85GB | + + + + +Original model description: +--- +license: apache-2.0 +language: +- en +tags: +- moe +- olmo +- olmoe +co2_eq_emissions: 1 +datasets: +- allenai/ultrafeedback_binarized_cleaned +base_model: allenai/OLMoE-1B-7B-0924-SFT +library_name: transformers +--- + +OLMoE Logo. + +# Model Summary + +> OLMoE-1B-7B-Instruct is a Mixture-of-Experts LLM with 1B active and 7B total parameters released in September 2024 (0924) that has been adapted via SFT and DPO from [OLMoE-1B-7B](https://hf.co/allenai/OLMoE-1B-7B-0924). It yields state-of-the-art performance among models with a similar cost (1B) and is competitive with much larger models like Llama2-13B-Chat. OLMoE is 100% open-source. + +This information and more can also be found on the [**OLMoE GitHub repository**](https://github.com/allenai/OLMoE). +- **Paper**: https://arxiv.org/abs/2409.02060 +- **Pretraining** [Checkpoints](https://hf.co/allenai/OLMoE-1B-7B-0924), [Code](https://github.com/allenai/OLMo/tree/Muennighoff/MoE), [Data](https://huggingface.co/datasets/allenai/OLMoE-mix-0924) and [Logs](https://wandb.ai/ai2-llm/olmoe/reports/OLMoE-1B-7B-0924--Vmlldzo4OTcyMjU3). +- **SFT (Supervised Fine-Tuning)** [Checkpoints](https://huggingface.co/allenai/OLMoE-1B-7B-0924-SFT), [Code](https://github.com/allenai/open-instruct/tree/olmoe-sft), [Data](https://hf.co/datasets/allenai/tulu-v3.1-mix-preview-4096-OLMoE) and [Logs](https://github.com/allenai/OLMoE/blob/main/logs/olmoe-sft-logs.txt). +- **DPO/KTO (Direct Preference Optimization/Kahneman-Tversky Optimization)**, [Checkpoints](https://huggingface.co/allenai/OLMoE-1B-7B-0924-Instruct), [Preference Data](https://hf.co/datasets/allenai/ultrafeedback_binarized_cleaned), [DPO code](https://github.com/allenai/open-instruct/tree/olmoe-sft), [KTO code](https://github.com/Muennighoff/kto/blob/master/kto.py) and [Logs](https://github.com/allenai/OLMoE/blob/main/logs/olmoe-dpo-logs.txt). + +# Use + +Install `transformers` **from source** until a release after [this PR](https://github.com/huggingface/transformers/pull/32406) & `torch` and run: + +```python +from transformers import OlmoeForCausalLM, AutoTokenizer +import torch + +DEVICE = "cuda" if torch.cuda.is_available() else "cpu" + +# Load different ckpts via passing e.g. `revision=kto` +model = OlmoeForCausalLM.from_pretrained("allenai/OLMoE-1B-7B-0924-Instruct").to(DEVICE) +tokenizer = AutoTokenizer.from_pretrained("allenai/OLMoE-1B-7B-0924-Instruct") +messages = [{"role": "user", "content": "Explain to me like I'm five what is Bitcoin."}] +inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(DEVICE) +out = model.generate(inputs, max_length=100) +print(tokenizer.decode(out[0])) +""" +<|endoftext|><|user|> +Explain to me like I'm five what is Bitcoin. +<|assistant|> +Bitcoin is like a special kind of money that you can use to buy things online. But unlike regular money, like dollars or euros, Bitcoin isn't printed by governments or banks. Instead, it's created by a special computer program that helps people keep track of it. + +Here's how it works: imagine you have a bunch of toys, and you want to +""" +``` + +Branches: +- `main`: Preference tuned via DPO model of https://hf.co/allenai/OLMoE-1B-7B-0924-SFT (`main` branch) +- `load-balancing`: Ablation with load balancing loss during DPO starting from the `load-balancing` branch of https://hf.co/allenai/OLMoE-1B-7B-0924-SFT +- `non-annealed`: Ablation starting from the `non-annealed` branch of https://hf.co/allenai/OLMoE-1B-7B-0924-SFT which is an SFT of the pretraining checkpoint prior to annealing (branch `step1200000-tokens5033B` of https://hf.co/allenai/OLMoE-1B-7B-0924) +- `kto`: Ablation using KTO instead of DPO. This branch is the checkpoint after 5,000 steps with the RMS optimizer. The other `kto*` branches correspond to the other checkpoints mentioned in the paper. + +# Evaluation Snapshot + +| Task (→) | MMLU | GSM8k | BBH | Human-Eval | Alpaca-Eval 1.0 | XSTest | IFEval | Avg | +|---------------|------|-------|------|------------|-----------------|--------|--------|------| +| **Setup (→)** | 0-shot | 8-shot CoT | 3-shot | 0-shot | 0-shot | 0-shot | 0-shot | | +| **Metric (→)** | EM | EM | EM | Pass@10 | %win | F1 | Loose Acc | | +| | | | | | | | | | +| OLMo-1B (0724) | 25.0 | 7.0 | 22.5 | 16.0 | - | 67.6 | 20.5 | - | +| +SFT | 36.0 | 12.5 | 27.2 | 21.2 | 41.5 | 81.9 | 26.1 | 35.9 | +| +DPO | 36.7 | 12.5 | 30.6 | 22.0 | 50.9 | 79.8 | 24.2 | 37.4 | +| OLMo-7B (0724) | 50.8 | 32.5 | 36.9 | 32.3 | - | 80.8 | 19.6 | - | +| +SFT | 54.2 | 25.0 | 35.7 | 38.5 | 70.9 | 86.1 | 39.7 | 49.3 | +| +DPO | 52.8 | 9.0 | 16.6 | 35.0 | 83.5 | **87.5** | 37.9 | 49.1 | +| JetMoE-2B-9B | 45.6 | 43.0 | 37.2 | 54.6 | - | 68.2 | 20.0 | - | +| +SFT | 46.1 | 53.5 | 35.6 | 64.8 | 69.3 | 55.6 | 30.5 | 50.4 | +| DeepSeek-3B-16B | 37.7 | 18.5 | 39.4 | 48.3 | - | 65.9 | 13.5 | - | +| +Chat | 48.5 | 46.5 | **40.8** | **70.1** | 74.8 | 85.6 | 32.3 | 57.0 | +| Qwen1.5-3B-14B | **60.4** | 13.5 | 27.2 | 60.2 | - | 73.4 | 20.9 | - | +| +Chat | 58.9 | **55.5** | 21.3 | 59.7 | 83.9 | 85.6 | 36.2 | 57.3 | +| **OLMoE (This Model)** | 49.8 | 3.0 | 33.6 | 22.4 | - | 59.7 | 16.6 | - | +| **+SFT** | 51.4 | 40.5 | 38.0 | 51.6 | 69.2 | 84.1 | 43.3 | 54.0 | +| **+DPO** | 51.9 | 45.5 | 37.0 | 54.8 | **84.0** | 82.6 | **48.1** | **57.7** | + +# Citation + +```bibtex +@misc{muennighoff2024olmoeopenmixtureofexpertslanguage, + title={OLMoE: Open Mixture-of-Experts Language Models}, + author={Niklas Muennighoff and Luca Soldaini and Dirk Groeneveld and Kyle Lo and Jacob Morrison and Sewon Min and Weijia Shi and Pete Walsh and Oyvind Tafjord and Nathan Lambert and Yuling Gu and Shane Arora and Akshita Bhagia and Dustin Schwenk and David Wadden and Alexander Wettig and Binyuan Hui and Tim Dettmers and Douwe Kiela and Ali Farhadi and Noah A. Smith and Pang Wei Koh and Amanpreet Singh and Hannaneh Hajishirzi}, + year={2024}, + eprint={2409.02060}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2409.02060}, +} +``` +