diff --git a/config.json b/config.json index e525507..b483159 100644 --- a/config.json +++ b/config.json @@ -10,7 +10,7 @@ "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 32768, - "max_window_layers": 21, + "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 12, "num_hidden_layers": 28, diff --git a/generation_config.json b/generation_config.json index c5c3810..b7849b3 100644 --- a/generation_config.json +++ b/generation_config.json @@ -10,5 +10,5 @@ "temperature": 0.7, "top_p": 0.8, "top_k": 20, - "transformers_version": "4.37.0" -} \ No newline at end of file + "transformers_version": "4.44.0" +} diff --git a/tokenizer_config.json b/tokenizer_config.json index 07bfe06..acee076 100644 --- a/tokenizer_config.json +++ b/tokenizer_config.json @@ -199,9 +199,9 @@ "clean_up_tokenization_spaces": false, "eos_token": "<|im_end|>", "errors": "replace", - "model_max_length": 131072, + "model_max_length": 32768, "pad_token": "<|endoftext|>", "split_special_tokens": false, "tokenizer_class": "Qwen2Tokenizer", "unk_token": null -} \ No newline at end of file +}