|
{ |
|
"_name_or_path": "galactica-125m", |
|
"_remove_final_layer_norm": false, |
|
"activation_dropout": 0.0, |
|
"activation_function": "gelu", |
|
"architectures": [ |
|
"OPTForCausalLM" |
|
], |
|
"attention_dropout": 0.1, |
|
"bos_token_id": 0, |
|
"do_layer_norm_before": true, |
|
"dropout": 0.1, |
|
"enable_bias": true, |
|
"eos_token_id": 2, |
|
"ffn_dim": 3072, |
|
"hidden_size": 768, |
|
"init_std": 0.02, |
|
"layer_norm_elementwise_affine": true, |
|
"layerdrop": 0.0, |
|
"learned_embeddings": true, |
|
"max_position_embeddings": 2048, |
|
"model_type": "opt", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"pad_token_id": 1, |
|
"quantization_config": { |
|
"_load_in_4bit": true, |
|
"_load_in_8bit": false, |
|
"bnb_4bit_compute_dtype": "float32", |
|
"bnb_4bit_quant_storage": "uint8", |
|
"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": true, |
|
"load_in_8bit": false, |
|
"quant_method": "bitsandbytes" |
|
}, |
|
"scale_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.39.3", |
|
"use_cache": true, |
|
"vocab_size": 50000, |
|
"word_embed_proj_dim": 768 |
|
} |
|
|