File size: 1,733 Bytes
69c8fbe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
{
"_name_or_path": "tiiuae/falcon-rw-1b",
"alibi": true,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"FalconForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
"AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
"AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
"AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
"AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
"AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
},
"bias": true,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_dropout": 0.0,
"hidden_size": 2048,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "falcon",
"multi_query": false,
"new_decoder_architecture": false,
"num_attention_heads": 32,
"num_hidden_layers": 24,
"num_kv_heads": 32,
"parallel_attn": false,
"quantization_config": {
"batch_size": 1,
"bits": 4,
"block_name_to_quantize": "transformer.h",
"damp_percent": 0.1,
"dataset": "c4",
"desc_act": false,
"disable_exllama": false,
"group_size": 128,
"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": "4.32.0",
"use_cache": true,
"vocab_size": 50304
}
|