class Olmo3Config(PretrainedConfig):
model_type = "olmo3"
keys_to_ignore_at_inference = ["past_key_values"]
def __init__(
self,
vocab_size=50304,
hidden_size=4096,
intermediate_size=11008,
num_hidden_layers=32,
num_attention_heads=32,
num_key_value_heads=None,
hidden_act="silu",
max_position_embeddings=2048,
initializer_range=0.02,
use_cache=True,
pad_token_id=1,
bos_token_id=None,
eos_token_id=50279,
tie_word_embeddings=False,
rope_theta=10000.0,
rope_scaling=None,
attention_bias=False,
attention_dropout=0.0,
rms_norm_eps=1e-5,
sliding_window=4096,
layer_types=None,
**kwargs,
):
# This model uses Olmo3ForCausalLM in transformers but Olmo2ForCausalLM
# in vLLM.
if "architectures" not in kwargs:
kwargs["architectures"] = ["Olmo2ForCausalLM"]
elif "Olmo3ForCausalLM" in kwargs["architectures"]:
kwargs["architectures"].remove("Olmo3ForCausalLM")
kwargs["architectures"].append("Olmo2ForCausalLM")
super().__init__(
pad_token_id=pad_token_id,
bos_token_id=bos_token_id,
eos_token_id=eos_token_id,
tie_word_embeddings=tie_word_embeddings,
**kwargs,
)
self.vocab_size = vocab_size
self.max_position_embeddings = max_position_embeddings
self.hidden_size = hidden_size
self.intermediate_size = intermediate_size
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
# for backward compatibility
if num_key_value_heads is None:
num_key_value_heads = num_attention_heads
self.num_key_value_heads = num_key_value_heads
self.hidden_act = hidden_act
self.initializer_range = initializer_range
self.use_cache = use_cache
self.rope_theta = rope_theta
self.rope_scaling = rope_scaling
self.attention_bias = attention_bias
self.attention_dropout = attention_dropout
self.rms_norm_eps = rms_norm_eps
self.sliding_window = sliding_window
self.layer_types = layer_types
if self.layer_types is None:
self.layer_types = [
"sliding_attention" if (i + 1) % 4 != 0 else "full_attention"
for i in range(self.num_hidden_layers)
]