{
  "_name_or_path": "/mnt/bd/bdriveyiranwang2/ds_chat_cosine_original_sppo/GT_ORIGINAL_MASKED-DeepSeek-LLM-c-rmsprop-sppo_hard-0.1-1e-7-cosine-Iter1-sft-reg-0.0-grad-accumulation-1/checkpoints/DeepSeek-Coder-7B-Instruct-SPPO-Iter1/checkpoint-782",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 100000,
  "eos_token_id": 100001,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 30,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.42.0",
  "use_cache": false,
  "vocab_size": 102400
}