cpu

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((...

Qwen2TokenizerFast(name_or_path='Qwen/Qwen2.5-0.5B', vocab_size=151643, model_max_length=131072, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'eos_token': '<|endoftext|>', 'pad_token': '<|endoftext|>', 'additional_special_tokens': ['<|im_start|>', '<|im_end|>', '<|object_ref_start|>', '<|object_ref_end|>', '<|box_start|>', '<|box_end|>', '<|quad_start|>', '<|quad_end|>', '<|vision_start|>', '<|vision_end|>', '<|vision_pad|>', '<|image_pad|>', '<|video_pad|>']}, clean_up_tokenization_spaces=False), added_tokens_decoder={ 151643: AddedToken("<|endoftext|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 151644: AddedToken("<|im_start|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 151645: AddedToken("<|im_end|>", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 151646: AddedToken("<|object_ref_start|>", rstrip=False, lstrip=False, single_word=False, nor...