|
{ |
|
"_name_or_path": "tiiuae/falcon-7b", |
|
"alibi": false, |
|
"apply_residual_connection_post_layernorm": false, |
|
"architectures": [ |
|
"FalconForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig", |
|
"AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel", |
|
"AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM", |
|
"AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering", |
|
"AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification", |
|
"AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification" |
|
}, |
|
"bias": false, |
|
"bos_token_id": 11, |
|
"eos_token_id": 11, |
|
"hidden_dropout": 0.0, |
|
"hidden_size": 4544, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"model_type": "falcon", |
|
"multi_query": true, |
|
"new_decoder_architecture": false, |
|
"num_attention_heads": 71, |
|
"num_hidden_layers": 32, |
|
"num_kv_heads": 71, |
|
"parallel_attn": true, |
|
"quantization_config": { |
|
"batch_size": 1, |
|
"bits": 4, |
|
"block_name_to_quantize": "transformer.h", |
|
"damp_percent": 0.1, |
|
"dataset": "c4", |
|
"desc_act": false, |
|
"disable_exllama": true, |
|
"group_size": 128, |
|
"max_input_length": null, |
|
"model_seqlen": 2048, |
|
"module_name_preceding_first_block": [ |
|
"transformer.word_embeddings" |
|
], |
|
"pad_token_id": null, |
|
"quant_method": "gptq", |
|
"sym": true, |
|
"tokenizer": null, |
|
"true_sequential": true, |
|
"use_cuda_fp16": true |
|
}, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.34.0", |
|
"use_cache": true, |
|
"vocab_size": 65024 |
|
} |
|
|