| type: pharia | |
| attention_bias: true | |
| attention_dropout: 0.0 | |
| eos_token_id: 0 | |
| bos_token_id: 127179 | |
| pad_token_id: 1 | |
| hidden_act: gelu | |
| hidden_size: 512 | |
| initializer_range: 0.02 | |
| intermediate_size: 1024 | |
| max_position_embeddings: 2048 | |
| mlp_bias: true | |
| num_attention_heads: 8 | |
| num_hidden_layers: 6 | |
| num_key_value_heads: 8 | |
| rope_scaling: null | |
| rope_theta: 1000000 | |
| tie_word_embeddings: false | |
| use_cache: true | |
| context_length: 2048 | |
| vocab_size: 178 | |