{ | |
"_name_or_path": "/workspace/models/ehartford_samantha-falcon-7b", | |
"alibi": false, | |
"apply_residual_connection_post_layernorm": false, | |
"architectures": [ | |
"RWForCausalLM" | |
], | |
"attention_dropout": 0.0, | |
"auto_map": { | |
"AutoConfig": "configuration_RW.RWConfig", | |
"AutoModelForCausalLM": "modelling_RW.RWForCausalLM" | |
}, | |
"bias": false, | |
"bos_token_id": 1, | |
"eos_token_id": 2, | |
"hidden_dropout": 0.0, | |
"hidden_size": 4544, | |
"initializer_range": 0.02, | |
"layer_norm_epsilon": 1e-05, | |
"model_type": "RefinedWebModel", | |
"multi_query": true, | |
"n_head": 71, | |
"n_layer": 32, | |
"parallel_attn": true, | |
"torch_dtype": "bfloat16", | |
"transformers_version": "4.30.0.dev0", | |
"use_cache": true, | |
"vocab_size": 65024, | |
"quantization_config": { | |
"bits": 4, | |
"group_size": 64, | |
"damp_percent": 0.01, | |
"desc_act": true, | |
"sym": true, | |
"true_sequential": true, | |
"model_name_or_path": null, | |
"model_file_base_name": "model", | |
"quant_method": "gptq" | |
} | |
} |