| |
| |
| |
| |
|
|
| from transformers import PretrainedConfig |
|
|
|
|
| class MonkeyConfig(PretrainedConfig): |
| model_type = "monkey" |
| keys_to_ignore_at_inference = ["past_key_values"] |
|
|
| def __init__( |
| self, |
| vocab_size=151936, |
| hidden_size=4096, |
| num_hidden_layers=32, |
| num_attention_heads=32, |
| emb_dropout_prob=0.0, |
| attn_dropout_prob=0.0, |
| layer_norm_epsilon=1e-6, |
| initializer_range=0.02, |
| max_position_embeddings=8192, |
| scale_attn_weights=True, |
| use_cache=True, |
| bf16=False, |
| fp16=False, |
| fp32=False, |
| kv_channels=128, |
| rotary_pct=1.0, |
| rotary_emb_base=10000, |
| use_dynamic_ntk=True, |
| use_logn_attn=True, |
| use_flash_attn="auto", |
| intermediate_size=22016, |
| no_bias=True, |
| tie_word_embeddings=False, |
| **kwargs, |
| ): |
| self.vocab_size = vocab_size |
| self.hidden_size = hidden_size |
| self.intermediate_size = intermediate_size |
| self.num_hidden_layers = num_hidden_layers |
| self.num_attention_heads = num_attention_heads |
| self.emb_dropout_prob = emb_dropout_prob |
| self.attn_dropout_prob = attn_dropout_prob |
| self.layer_norm_epsilon = layer_norm_epsilon |
| self.initializer_range = initializer_range |
| self.scale_attn_weights = scale_attn_weights |
| self.use_cache = use_cache |
| self.max_position_embeddings = max_position_embeddings |
| self.bf16 = bf16 |
| self.fp16 = fp16 |
| self.fp32 = fp32 |
| self.kv_channels = kv_channels |
| self.rotary_pct = rotary_pct |
| self.rotary_emb_base = rotary_emb_base |
| self.use_dynamic_ntk = use_dynamic_ntk |
| self.use_logn_attn = use_logn_attn |
| self.use_flash_attn = use_flash_attn |
| self.no_bias = no_bias |
| super().__init__( |
| tie_word_embeddings=tie_word_embeddings, |
| **kwargs |
| ) |
|
|
