| {"vocab_size": 65024, "hidden_size": 4544, "num_hidden_layers": 32, "num_attention_heads": 71, "layer_norm_epsilon": 1e-05, "initializer_range": 0.02, "use_cache": true, "hidden_dropout": 0.0, "attention_dropout": 0.0, "bos_token_id": 11, "eos_token_id": 11, "num_kv_heads": 71, "alibi": false, "new_decoder_architecture": false, "multi_query": true, "parallel_attn": true, "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": true, "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, "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": ["FalconForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "pad_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded", "transformers_version": "4.32.0.dev0", "apply_residual_connection_post_layernorm": false, "auto_map": {"AutoConfig": "vilsonrodrigues/falcon-7b-instruct-sharded--configuration_falcon.FalconConfig", "AutoModel": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconModel", "AutoModelForSequenceClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForSequenceClassification", "AutoModelForTokenClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForTokenClassification", "AutoModelForQuestionAnswering": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForQuestionAnswering", "AutoModelForCausalLM": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForCausalLM"}, "model_type": "falcon", "quantization_config": {"quant_method": "bitsandbytes", "load_in_8bit": false, "load_in_4bit": true, "llm_int8_threshold": 6.0, "llm_int8_skip_modules": null, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": true, "bnb_4bit_compute_dtype": "bfloat16"}} |