| { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "./entity-3b-censored", |
| "architectures": [ |
| "EntityForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 128000, |
| "eos_token_id": [ |
| 128001, |
| 128008, |
| 128009 |
| ], |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 3072, |
| "initializer_range": 0.02, |
| "intermediate_size": 8192, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "model_type": "entity", |
| "num_attention_heads": 24, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 8, |
| "pretraining_tp": 1, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "factor": 32.0, |
| "high_freq_factor": 4.0, |
| "low_freq_factor": 1.0, |
| "original_max_position_embeddings": 8192, |
| "rope_type": "entity" |
| }, |
| "rope_theta": 500000.0, |
| "sapiens_transformers_version": "1.2.6", |
| "tie_word_embeddings": true, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.44.2", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
|
|
