config.json

{
  "_name_or_path": "/mnt/fs-arf-01/tai/sft/llamafactory_sft/complete/simpo/lf_llama3_8b_CPTHRUN2_sftqlora_com0.3Wselfmagpiehigh_llama3tmp_simpoqlora_gemmaseafeedback",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "eos_token_id": 128001,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "init_device": "cpu",
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "llama",
  "name": "hf_causal_lm",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretrained": true,
  "pretrained_model_name_or_path": "/mnt/fs-arf-01/cpt_checkpoints/meta-llama/Meta-Llama-3-8B",
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.43.2",
  "trust_remote_code": true,
  "use_cache": true,
  "use_flash_attention_2": true,
  "vocab_size": 128256
}