config.json

{
  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
  "architectures": [
    "QStarLlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "qstar_config": {
    "base_loss_beta": 1.0,
    "embedding_scale": 100.0,
    "end_token_id": 128257,
    "gumbel_temperature": 1.0,
    "n_ahead": 8,
    "n_ahead_talk": 2,
    "n_passes": 1,
    "original_loss_weight": 0.5,
    "pad_token_id": 128001,
    "policy_loss_beta": 1000000.0,
    "reinforce_temperature": 3.0,
    "start_token_id": 128256,
    "thought_init_std_scale": 0.01
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "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": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.2",
  "use_cache": true,
  "vocab_size": 128258
}