update config

config.json

@@ -1 +1 @@
-{"mixer": {"l_max": 2048, "_target_": "based.models.mixers.convolution.BaseConv", "use_bias": true, "expand_proj": 4, "kernel_sizes": 3}, "vocab_size": 50257, "n_positions": 0, "n_embd": 1792, "n_layer": 36, "n_head": 16, "n_inner": 3584, "activation_function": "swiglu", "resid_pdrop": 0, "embd_pdrop": 0, "attn_pdrop": 0, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": null, "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.36.2", "rms_norm": true, "fused_mlp": false, "decay_const": -3, "decay_denom": false, "fixed_decay": true, "mlp_fc1_bias": false, "mlp_fc2_bias": false, "fused_bias_fc": true, "out_proj_bias": false, "qkv_proj_bias": false, "use_flash_attn": true, "alt_mixer": {"l_max": 2048, "_target_": "based.models.mixers.linear_attention.LinearAttention", "num_heads": 16, "feature_dim": 16, "parallel_implementation": "fla_parallel", "feature_map": {"_target_": "based.models.mixers.linear_attention.TaylorExp", "input_dim": 16}}, "alt_mixer_layers": [1, 6, 11, 16, 21, 27, 33], "residual_in_fp32": true, "alt_mixer_2": {"causal": true, "_target_": "based.models.mixers.slide_attention.SlidingAttention", "num_heads": 16, "window_size": 256}, "alt_mixer_2_layers": [2, 7, 12, 17, 22, 28, 34], "rotary_emb_fraction": 1, "special_initializer": true, "fused_dropout_add_ln": true, "pad_vocab_size_multiple": 8, "model_type": "gpt2"}
+{"mixer": {"l_max": 2048, "_target_": "based.models.mixers.convolution.BaseConv", "use_bias": true, "expand_proj": 4, "kernel_sizes": 3}, "vocab_size": 50257, "n_positions": 0, "n_embd": 1792, "n_layer": 36, "n_head": 16, "n_inner": 3584, "activation_function": "swiglu", "resid_pdrop": 0, "embd_pdrop": 0, "attn_pdrop": 0, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "summary_type": "cls_index", "summary_use_proj": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "scale_attn_weights": true, "use_cache": true, "scale_attn_by_inverse_layer_idx": false, "reorder_and_upcast_attn": false, "bos_token_id": 50256, "eos_token_id": 50256, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": null, "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "transformers_version": "4.36.2", "rms_norm": true, "fused_mlp": false, "decay_const": -3, "decay_denom": false, "fixed_decay": false, "mlp_fc1_bias": false, "mlp_fc2_bias": false, "fused_bias_fc": true, "out_proj_bias": false, "qkv_proj_bias": false, "use_flash_attn": true, "alt_mixer": {"l_max": 2048, "_target_": "based.models.mixers.linear_attention.LinearAttention", "num_heads": 16, "feature_dim": 16, "parallel_implementation": "fla_parallel", "feature_map": {"_target_": "based.models.mixers.linear_attention.TaylorExp", "input_dim": 16}}, "alt_mixer_layers": [1, 6, 11, 16, 21, 27, 33], "residual_in_fp32": true, "alt_mixer_2": {"causal": true, "_target_": "based.models.mixers.slide_attention.SlidingAttention", "num_heads": 16, "window_size": 256}, "alt_mixer_2_layers": [2, 7, 12, 17, 22, 28, 34], "rotary_emb_fraction": 1, "special_initializer": true, "fused_dropout_add_ln": true, "pad_vocab_size_multiple": 8, "model_type": "gpt2"}