falcon-wait3-v1 / config.json
maxolotl's picture
Upload RWForCausalLM
8ad9896
{
"_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
"alibi": false,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"RWForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
"AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
"AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
"AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
"AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
"AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
},
"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": "RefinedWebModel",
"multi_query": true,
"n_head": 71,
"n_layer": 32,
"parallel_attn": true,
"quantization_config": {
"bnb_4bit_compute_dtype": "float16",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": false,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": null,
"llm_int8_threshold": 6.0,
"load_in_4bit": false,
"load_in_8bit": true,
"quant_method": "bitsandbytes"
},
"torch_dtype": "float32",
"transformers_version": "4.32.1",
"use_cache": false,
"vocab_size": 65024
}