diff --git a/config.json b/config.json index 35cb791..e372918 100644 --- a/config.json +++ b/config.json @@ -2,7 +2,7 @@ "architectures": [ "MistralForCausalLM" ], - "attention_dropout": 0, + "attention_dropout": 0.1, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", diff --git a/model.safetensors b/model.safetensors index b5884cd..ab33463 100644 --- a/model.safetensors +++ b/model.safetensors @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9a565a3989b85cc64b7e0013120b3252fcff093b749f49485e005151bad8462f +oid sha256:87f2ed7ee62e26c7fcf6cccae2e4285eea2109e403d98d23e60d3d34697160ea size 140516640 diff --git a/training_args.bin b/training_args.bin index decfed7..326c162 100644 --- a/training_args.bin +++ b/training_args.bin @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8fb60741b16ac8a592f18de1dbe51176dc5bc594e36171dd5e392551ea9c859a +oid sha256:7c360e48bc9afd83a98d0e8238647289d95d71f1e4fe9936279100540ef3782e size 5944