| bias: false | |
| block_size: 2048 | |
| gelu_approximate: none | |
| head_size: 64 | |
| hf_config: | |
| name: TinyLlama-1.1B-intermediate-step-1431k-3T | |
| org: TinyLlama | |
| intermediate_size: 5632 | |
| lm_head_bias: false | |
| mlp_class_name: LLaMAMLP | |
| n_embd: 2048 | |
| n_expert: 0 | |
| n_expert_per_token: 0 | |
| n_head: 32 | |
| n_layer: 22 | |
| n_query_groups: 4 | |
| name: tiny-llama-1.1b | |
| norm_class_name: RMSNorm | |
| norm_eps: 1.0e-05 | |
| padded_vocab_size: 32000 | |
| padding_multiple: 64 | |
| parallel_residual: false | |
| rope_base: 10000 | |
| rope_condense_ratio: 1 | |
| rotary_percentage: 1.0 | |
| scale_embeddings: false | |
| shared_attention_norm: false | |
| vocab_size: 32000 | |