DaertML's picture
ADD BNB model
3979ad7
{
"_name_or_path": "microsoft/phi-1",
"activation_function": "gelu_new",
"architecture": {
"block_cls": "parallel",
"mixer": {},
"mlp": {
"mlp_cls": "mlp"
}
},
"architectures": [
"MixFormerSequentialForCausalLM"
],
"auto_map": {
"AutoConfig": "microsoft/phi-1--configuration_mixformer_sequential.MixFormerSequentialConfig",
"AutoModelForCausalLM": "microsoft/phi-1--modeling_mixformer_sequential.MixFormerSequentialForCausalLM"
},
"embd_layer": "default",
"embd_pdrop": 0.0,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "mixformer-sequential",
"n_embd": 2048,
"n_head": 32,
"n_inner": null,
"n_layer": 24,
"n_positions": 2048,
"phyagi_version": "0.0.4.dev",
"quantization_config": {
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"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"
},
"resid_pdrop": 0.0,
"rotary_dim": 32,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.33.1",
"vocab_size": 51200
}