ornith-ai/Ornith-1.5-9B config.json

Fetched 2026-10-18 from resolve/main/config.json. architectures Qwen3_5ForConditionalGeneration, model_type qwen3_5. text_config: hidden_size 4096, num_hidden_layers 32, num_attention_heads 16, num_key_value_heads 4, head_dim 256, intermediate_size 12288, vocab_size 248320, max_position_embeddings 262144, hidden_act silu, tie_word_embeddings false, partial_rotary_factor 0.25. layer_types is 24 linear_attention + 8 full_attention. No num_experts key and no rope_scaling key.