| {"vocab_size": 128256, "max_position_embeddings": 131072, "hidden_size": 8192, "intermediate_size": 28672, "num_hidden_layers": 80, "num_attention_heads": 64, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": false, "rope_theta": 500000.0, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "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, "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": ["LlamaForCausalLM"], "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": 128000, "pad_token_id": null, "eos_token_id": [128001, 128008, 128009], "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct", "transformers_version": "4.44.1", "model_type": "llama", "qlora_config": {"lora_target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"], "compute_dtype": "bfloat16", "lora_rank": 64, "lora_alpha": 16, "lora_dropout": 0.1, "layer_nbits": {"q_proj": 4, "k_proj": 4, "v_proj": 4, "o_proj": 4, "gate_proj": 2, "up_proj": 2, "down_proj": 2}, "layer_groupsizes": {"q_proj": 128, "k_proj": 128, "v_proj": 128, "o_proj": 128, "gate_proj": 32, "up_proj": 32, "down_proj": 32}, "skip_dora_all": false, "skip_dora_4bit": false, "train_layernorms": 1, "groupsize_4bit": 128, "groupsize_2bit": 32, "block_influence_layers": ["layers.0", "layers.13", "layers.15", "layers.17", "layers.19", "layers.21", "layers.23", "layers.26", "layers.29", "layers.31", "layers.33", "layers.56", "layers.59", "layers.68", "layers.71", "layers.79"]}} |