| { |
| "architectures": [ |
| "AsteriskForCausalLM" |
| ], |
| "aspp_dropout": 0.15, |
| "aspp_hidden_dim": 512, |
| "aspp_num_neighbors": 1, |
| "aspp_num_steps": 6, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "AsteriskForCausalLM.AsteriskConfig", |
| "AutoModelForCausalLM": "AsteriskForCausalLM.AsteriskForCausalLM" |
| }, |
| "bos_token_id": 128000, |
| "dtype": "bfloat16", |
| "eos_token_id": 128009, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "hybrid_layer_indices": null, |
| "initializer_range": 0.02, |
| "intermediate_size": 8192, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "model_type": "asterisk", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 16, |
| "num_key_value_heads": 8, |
| "pad_token_id": 128009, |
| "pi_flow": true, |
| "pi_flow_scale": 0.4, |
| "pi_flow_steps": 4, |
| "pi_flow_use_gate": true, |
| "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": "llama3" |
| }, |
| "rope_theta": 500000.0, |
| "tie_word_embeddings": true, |
| "transformers_version": "4.57.6", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
|
|
