| attention_logit_softcapping: null | |
| attention_scores_scalar: null | |
| attn_bias: true | |
| bias: false | |
| block_size: 32768 | |
| final_logit_softcapping: null | |
| gelu_approximate: none | |
| head_size: 128 | |
| hf_config: | |
| name: Qwen2.5-3B | |
| org: Qwen | |
| intermediate_size: 11008 | |
| lm_head_bias: false | |
| mlp_class_name: LLaMAMLP | |
| n_embd: 2048 | |
| n_expert: 0 | |
| n_expert_per_token: 0 | |
| n_head: 16 | |
| n_layer: 36 | |
| n_query_groups: 2 | |
| name: Qwen2.5-3B | |
| norm_class_name: RMSNorm | |
| norm_eps: 1.0e-06 | |
| norm_qk: false | |
| padded_vocab_size: 151936 | |
| padding_multiple: 512 | |
| parallel_residual: false | |
| post_attention_norm: false | |
| post_mlp_norm: false | |
| rope_adjustments: null | |
| rope_base: 1000000 | |
| rope_condense_ratio: 1 | |
| rotary_percentage: 1.0 | |
| scale_embeddings: false | |
| shared_attention_norm: false | |
| sliding_window_layer_placing: null | |
| sliding_window_size: null | |
| vocab_size: 151643 | |