Files
Neo50M/training_configs/model_neo50m.yaml

22 lines
519 B
YAML
Raw Permalink Normal View History

model:
name: Neo50M
architecture: llama
tokenizer_id: TinyLlama/TinyLlama-1.1B-Chat-v1.0
hidden_size: 512
intermediate_size: 1536
num_hidden_layers: 12
num_attention_heads: 8
num_key_value_heads: 2
max_position_embeddings: 16384
rope_theta: 500000.0
rms_norm_eps: 0.000001
initializer_range: 0.02
tie_word_embeddings: true
use_cache: false
attention_dropout: 0.0
attention_bias: false
mlp_bias: false
attn_implementation: sdpa
gradient_checkpointing: false
torch_dtype: bfloat16