| {'vocab_size': 32000, | |
| 'max_position_embeddings': 4096, | |
| 'hidden_size': 4096, | |
| 'intermediate_size': 11008, | |
| 'num_hidden_layers': 32, | |
| 'num_attention_heads': 32, | |
| 'num_key_value_heads': 32, | |
| 'hidden_act': 'silu', | |
| 'initializer_range': 0.02, | |
| 'rms_norm_eps': 1e-05, | |
| 'pretraining_tp': 1, | |
| 'use_cache': False, | |
| 'rope_scaling': None, | |
| 'return_dict': True, | |
| 'output_hidden_states': False, | |
| 'output_attentions': False, | |
| 'torchscript': False, | |
| 'torch_dtype': 'float16', | |
| 'use_bfloat16': False, | |
| 'tf_legacy_loss': False, | |
| 'pruned_heads': {}, | |
| 'tie_word_embeddings': False, | |
| 'is_encoder_decoder': False, | |
| 'is_decoder': False, | |
| 'cross_attention_hidden_size': None, | |
| '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': None, | |
| 'num_return_sequences': 1, | |
| 'chunk_size_feed_forward': 0, | |
| 'output_scores': False, | |
| 'return_dict_in_generate': False, | |
| 'forced_bos_token_id': None, | |
| 'forced_eos_token_id': None, | |
| 'remove_invalid_values': False, | |
| 'exponential_decay_length_penalty': None, | |
| 'suppress_tokens': None, | |
| 'begin_suppress_tokens': None, | |
| 'architectures': ['LlamaForCausalLM'], | |
| 'finetuning_task': None, | |
| 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, | |
| 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, | |
| 'tokenizer_class': None, | |
| 'prefix': None, | |
| 'bos_token_id': 1, | |
| 'pad_token_id': None, | |
| 'eos_token_id': 2, | |
| 'sep_token_id': None, | |
| 'decoder_start_token_id': None, | |
| 'task_specific_params': None, | |
| 'problem_type': None, | |
| '_name_or_path': 'mahimairaja/tweet-summarization-llama-2-finetuned', | |
| 'transformers_version': '4.32.1', | |
| 'model_type': 'llama', | |
| 'quantization_config': {'quant_method': <QuantizationMethod.BITS_AND_BYTES: 'bitsandbytes'>, | |
| 'load_in_8bit': False, | |
| 'load_in_4bit': True, | |
| 'llm_int8_threshold': 6.0, | |
| 'llm_int8_skip_modules': None, | |
| 'llm_int8_enable_fp32_cpu_offload': False, | |
| 'llm_int8_has_fp16_weight': False, | |
| 'bnb_4bit_quant_type': 'nf4', | |
| 'bnb_4bit_use_double_quant': False, | |
| 'bnb_4bit_compute_dtype': 'float16'}} |