update

config.json

@@ -1,4 +1,5 @@
-{  "auto_map": {
+{  
+  "auto_map": {
     "AutoConfig": "configuration_geblm.GEBConfig",
     "AutoModel": "modeling_geb.GEBForCausalLM"
-  }, "num_layers": 24, "padded_vocab_size": 64896, "hidden_size": 2048, "ffn_hidden_size": 5632, "kv_channels": 128, "num_attention_heads": 16, "torch_dtype": "bfloat16", "seq_length": 4096, "hidden_dropout": 0.0, "attention_dropout": 0.0, "layernorm_epsilon": 1e-05, "max_position_embeddings": 4096, "bias_dropout_fusion": true, "use_cache": true, "apply_residual_connection_post_layernorm": false, "post_layer_norm": true, "add_bias_linear": false, "use_flash_attn": false, "num_key_value_heads": 4, "apply_query_key_layer_scaling": false, "attention_softmax_in_fp32": false, "fp32_residual_connection": false, "pre_seq_len": null, "prefix_projection": false, "tie_word_embeddings": false, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "use_bfloat16": true, "tf_legacy_loss": false, "pruned_heads": {}, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 512, "min_length": 0, "do_sample": true, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 0.3, "top_k": 5, "top_p": 0.5, "typical_p": 1.0, "repetition_penalty": 1.15, "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": ["GEBForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 1, "eos_token_id": 2, "pad_token_id": 2, "_name_or_path": "", "transformers_version": "4.35.2", "model_type": "geblm"}
+  }, "num_layers": 24, "padded_vocab_size": 64896, "hidden_size": 2048, "ffn_hidden_size": 5632, "kv_channels": 128, "num_attention_heads": 16, "torch_dtype": "bfloat16", "seq_length": 4096, "hidden_dropout": 0.0, "attention_dropout": 0.0, "layernorm_epsilon": 1e-05, "max_position_embeddings": 4096, "bias_dropout_fusion": true, "use_cache": true, "apply_residual_connection_post_layernorm": false, "post_layer_norm": true, "add_bias_linear": false, "use_flash_attn": false, "num_key_value_heads": 4, "apply_query_key_layer_scaling": false, "attention_softmax_in_fp32": false, "fp32_residual_connection": false, "pre_seq_len": null, "prefix_projection": false, "tie_word_embeddings": false, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "use_bfloat16": true, "tf_legacy_loss": false, "pruned_heads": {}, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 512, "min_length": 0, "do_sample": true, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 0.3, "top_k": 5, "top_p": 0.5, "typical_p": 1.0, "repetition_penalty": 1.15, "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": ["GEBForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 1, "eos_token_id": 2, "pad_token_id": 2, "_name_or_path": "GEB-AGI/geb-1.3b", "transformers_version": "4.35.2", "model_type": "geblm"}