| { | |
| "_name_or_path": "cache/qstar/1710326256/checkpoint-100", | |
| "architectures": [ | |
| "QStarMistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "qstar_config": { | |
| "base_loss_beta": 1.0, | |
| "embedding_scale": 100.0, | |
| "end_token_id": 32000, | |
| "gumbel_temperature": 1.0, | |
| "n_ahead": 8, | |
| "n_ahead_talk": 1, | |
| "n_passes": 2, | |
| "original_loss_weight": 0.5, | |
| "pad_token_id": 2, | |
| "policy_loss_beta": 1000000.0, | |
| "reinforce_temperature": 3.0, | |
| "start_token_id": 32001, | |
| "thought_init_std_scale": 0.01 | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.4", | |
| "use_cache": true, | |
| "vocab_size": 32002 | |
| } | |