Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(151936, 896)
    (layers): ModuleList(
      (0-23): 24 x Qwen2DecoderLayer(
        (self_attn): Qwen2SdpaAttention(
          (q_proj): Linear(in_features=896, out_features=896, bias=True)
          (k_proj): Linear(in_features=896, out_features=128, bias=True)
          (v_proj): Linear(in_features=896, out_features=128, bias=True)
          (o_proj): Linear(in_features=896, out_features=896, bias=False)
          (rotary_emb): Qwen2RotaryEmbedding()
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=896, out_features=4864, bias=False)
          (up_proj): Linear(in_features=896, out_features=4864, bias=False)
          (down_proj): Linear(in_features=4864, out_features=896, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((896,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((896,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((896,), eps=1e-06)
  )
  (lm_head): Linear(in_features=896, out_features=151936, bias=False)
)