| { |
| "_non_freeze_layers_idxs": null, |
| "activation_checkpoint_layers_num": null, |
| "add_eos": true, |
| "add_pad_token": true, |
| "apply_torch_compile_to_projections": true, |
| "architectures": [ |
| "GigarEmbedModel" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_gigarembed.GigarEmbedConfig", |
| "AutoModel": "modeling_gigarembed.GigarEmbedModel" |
| }, |
| "hidden_size": 2048, |
| "is_mask_instruction": true, |
| "latent_attention_config": { |
| "_attn_implementation_autoset": false, |
| "add_cross_attention": false, |
| "architectures": null, |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "cross_dim_head": 2048, |
| "decoder_start_token_id": null, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "early_stopping": false, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": null, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "hidden_dim": 2048, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "latent_dim": 2048, |
| "length_penalty": 1.0, |
| "max_length": 20, |
| "min_length": 0, |
| "model_type": "latent_attention", |
| "mult": 4, |
| "no_repeat_ngram_size": 0, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_cross_heads": 8, |
| "num_latents_value": 512, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": null, |
| "prefix": null, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "sep_token_id": null, |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": true, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torch_dtype": null, |
| "torchscript": false, |
| "typical_p": 1.0, |
| "use_bfloat16": false |
| }, |
| "mask_type": "b", |
| "model_type": "gigarembed", |
| "padding_side": "right", |
| "text_config": { |
| "_attn_implementation_autoset": false, |
| "add_cross_attention": false, |
| "apply_qk_norm": true, |
| "architectures": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attention_hidden_size": null, |
| "attention_type": "LlamaLatentAttention", |
| "bad_words_ids": null, |
| "begin_suppress_tokens": null, |
| "bos_token_id": 1, |
| "chunk_size_feed_forward": 0, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "delete_logits": true, |
| "deterministic_attention": false, |
| "diversity_penalty": 0.0, |
| "do_sample": false, |
| "early_stopping": false, |
| "enable_async_tp": false, |
| "encoder_no_repeat_ngram_size": 0, |
| "eos_token_id": 2, |
| "exponential_decay_length_penalty": null, |
| "finetuning_task": null, |
| "forced_bos_token_id": null, |
| "forced_eos_token_id": null, |
| "freeze_non_embed": false, |
| "fused_mlp": true, |
| "fused_mlp_checkpoint_lvl": 3, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "ignore_index": -100, |
| "init_device": "meta", |
| "initializer_range": 0.02, |
| "intermediate_size": 11008, |
| "is_decoder": false, |
| "is_encoder_decoder": false, |
| "kv_lora_rank": 1024, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "length_penalty": 1.0, |
| "lora_alpha": null, |
| "lora_r": null, |
| "loss_inplace_backward": false, |
| "max_length": 20, |
| "max_position_embeddings": 4096, |
| "max_window_layers": 36, |
| "min_length": 0, |
| "mla_config": { |
| "kv_lora_rank": 1024, |
| "q_lora_rank": 0, |
| "qk_nope_head_dim": 64, |
| "qk_rope_head_dim": 64, |
| "v_head_dim": 128 |
| }, |
| "mlp_bias": false, |
| "model_type": "gigar", |
| "mtp_loss_weight": 0.1, |
| "mtp_predictor_num": 1, |
| "no_repeat_ngram_size": 0, |
| "norm_type": "LlamaRMSNorm", |
| "num_attention_heads": 16, |
| "num_beam_groups": 1, |
| "num_beams": 1, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 16, |
| "num_return_sequences": 1, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "output_scores": false, |
| "pad_token_id": 2, |
| "parallel_embedding_type": "EmbeddingParallelEmbedding", |
| "prefix": null, |
| "pretraining_tp": 1, |
| "problem_type": null, |
| "pruned_heads": {}, |
| "q_lora_rank": 0, |
| "qk_nope_head_dim": 64, |
| "qk_rope_head_dim": 64, |
| "remove_invalid_values": false, |
| "repetition_penalty": 1.0, |
| "return_dict": true, |
| "return_dict_in_generate": false, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": null, |
| "rope_theta": 100000.0, |
| "sep_token_id": null, |
| "skip_init_tp_modules": true, |
| "sliding_window": null, |
| "sp_split_type": "equal", |
| "suppress_tokens": null, |
| "task_specific_params": null, |
| "temperature": 1.0, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": false, |
| "tokenizer_class": null, |
| "top_k": 50, |
| "top_p": 1.0, |
| "torch_dtype": null, |
| "torchscript": false, |
| "tp_group": null, |
| "tp_size": 1, |
| "typical_p": 1.0, |
| "unk_token_id": 0, |
| "use_bfloat16": false, |
| "use_cache": false, |
| "use_cache_force": false, |
| "use_custom_rotary_kernel": false, |
| "use_liger": false, |
| "use_mrope": false, |
| "use_mtp": true, |
| "use_sliding_window": false, |
| "v_head_dim": 128, |
| "varlen_input": true, |
| "vocab_size": 128256, |
| "z_loss_eps": 5e-05 |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.0" |
| } |
|
|
