| { | |
| "_name_or_path": "ai-sage/Giga-Embeddings-instruct", | |
| "add_eos": true, | |
| "add_pad_token": true, | |
| "architectures": [ | |
| "GigarEmbedModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_gigarembed.GigarEmbedConfig", | |
| "AutoModel": "modeling_gigarembed.GigarEmbedModel" | |
| }, | |
| "hidden_size": 2048, | |
| "is_mask_instruction": false, | |
| "latent_attention_config": { | |
| "cross_dim_head": 2048, | |
| "hidden_dim": 2048, | |
| "latent_dim": 2048, | |
| "model_type": "latent_attention" | |
| }, | |
| "mask_type": "b", | |
| "model_type": "gigarembed", | |
| "padding_side": "right", | |
| "text_config": { | |
| "_name_or_path": "ai-sage/Giga-Embeddings-instruct", | |
| "activation_checkpoint_layers_num": null, | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_hidden_size": null, | |
| "attention_type": "LlamaPackedAttention", | |
| "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, | |
| "deterministic_attention": false, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": 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": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "init_device": "meta", | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "loss_inplace_backward": true, | |
| "max_length": 20, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 36, | |
| "min_length": 0, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 27, | |
| "num_key_value_heads": 2, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 2, | |
| "prefix": null, | |
| "pretraining_tp": 1, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "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": 1300, | |
| "sep_token_id": null, | |
| "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": "float32", | |
| "torchscript": false, | |
| "tp_group": null, | |
| "tp_size": 1, | |
| "typical_p": 1.0, | |
| "unk_token_id": 0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "use_mrope": false, | |
| "use_sliding_window": false, | |
| "varlen_input": false, | |
| "vocab_size": 128256 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.0.dev0" | |
| } | |