abc7431/customModel
07
1{2 "_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",3 "alibi": false,4 "apply_residual_connection_post_layernorm": false,5 "architectures": [6 "FalconForCausalLM"7 ],8 "attention_dropout": 0.0,9 "auto_map": {10 "AutoConfig": "vilsonrodrigues/falcon-7b-instruct-sharded--configuration_falcon.FalconConfig",11 "AutoModel": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconModel",12 "AutoModelForCausalLM": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForCausalLM",13 "AutoModelForQuestionAnswering": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForQuestionAnswering",14 "AutoModelForSequenceClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForSequenceClassification",15 "AutoModelForTokenClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForTokenClassification"16 },17 "bias": false,18 "bos_token_id": 11,19 "eos_token_id": 11,20 "hidden_dropout": 0.0,21 "hidden_size": 4544,22 "initializer_range": 0.02,23 "layer_norm_epsilon": 1e-05,24 "model_type": "falcon",25 "multi_query": true,26 "new_decoder_architecture": false,27 "num_attention_heads": 71,28 "num_hidden_layers": 32,29 "num_kv_heads": 71,30 "parallel_attn": true,31 "quantization_config": {32 "bnb_4bit_compute_dtype": "bfloat16",33 "bnb_4bit_quant_type": "nf4",34 "bnb_4bit_use_double_quant": true,35 "llm_int8_enable_fp32_cpu_offload": false,36 "llm_int8_has_fp16_weight": false,37 "llm_int8_skip_modules": null,38 "llm_int8_threshold": 6.0,39 "load_in_4bit": true,40 "load_in_8bit": false41 },42 "torch_dtype": "bfloat16",43 "transformers_version": "4.30.0.dev0",44 "use_cache": false,45 "vocab_size": 6502446}47 