transformers/issue_38523_ignore_mismatched_error.txt at main · vbramhadevi/transformers · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
Model loaded successfully: Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(151936, 4096)
    (layers): ModuleList(
      (0-23): 24 x Qwen2DecoderLayer(
        (self_attn): Qwen2Attention(
          (q_proj): Linear(in_features=4096, out_features=4096, bias=True)
          (k_proj): Linear(in_features=4096, out_features=1024, bias=True)
          (v_proj): Linear(in_features=4096, out_features=1024, bias=True)
          (o_proj): Linear(in_features=4096, out_features=4096, bias=False)
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=4096, out_features=16384, bias=False)
          (up_proj): Linear(in_features=4096, out_features=16384, bias=False)
          (down_proj): Linear(in_features=16384, out_features=4096, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((4096,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((4096,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((4096,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=4096, out_features=151936, bias=False)
)