sharpenb's picture
65792076a71ed38c323dd2b6d049cb5b106887aef2b61164ab365cbb23c0b12e
b64b487 verified
raw
history blame
1.15 kB
{
"_name_or_path": "/tmp/tmprzjueaj3",
"_remove_final_layer_norm": false,
"activation_dropout": 0.0,
"activation_function": "relu",
"architectures": [
"OPTForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 2,
"do_layer_norm_before": false,
"dropout": 0.1,
"enable_bias": true,
"eos_token_id": 2,
"ffn_dim": 4096,
"hidden_size": 1024,
"init_std": 0.02,
"layer_norm_elementwise_affine": true,
"layerdrop": 0.0,
"max_position_embeddings": 2048,
"model_type": "opt",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 1,
"prefix": "</s>",
"quantization_config": {
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "fp4",
"bnb_4bit_use_double_quant": true,
"llm_int8_enable_fp32_cpu_offload": false,
"llm_int8_has_fp16_weight": false,
"llm_int8_skip_modules": [
"lm_head"
],
"llm_int8_threshold": 6.0,
"load_in_4bit": true,
"load_in_8bit": false,
"quant_method": "bitsandbytes"
},
"torch_dtype": "float16",
"transformers_version": "4.37.1",
"use_cache": true,
"vocab_size": 50272,
"word_embed_proj_dim": 512
}