| { | |
| "architectures": [ | |
| "PhariaForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_pharia.PhariaConfig", | |
| "AutoModelForCausalLM": "modeling_pharia.PhariaForCausalLM" | |
| }, | |
| "model_type": "pharia-v1", | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "eos_token_id": 0, | |
| "bos_token_id": 127179, | |
| "pad_token_id": 1, | |
| "hidden_act": "gelu", | |
| "hidden_size": 4608, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 18432, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": true, | |
| "num_attention_heads": 36, | |
| "num_hidden_layers": 27, | |
| "num_key_value_heads": 4, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.44.2", | |
| "use_cache": true, | |
| "vocab_size": 128000 | |
| } |