config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "/root/.cache/huggingface/hub/models--ByteDance-Seed--Stable-DiffCoder-8B-Instruct/snapshots/d0808fa34fa03de9163a29cabfc7107294a535a8",
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.1,
  "auto_map": {
    "AutoModelForCausalLM": "modeling_seed_diffcoder.SeedDiffcoderForCausalLM"
  },
  "bos_token_id": 0,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.009882118,
  "intermediate_size": 14336,
  "layer_norm_eps": null,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "resid_pdrop": 0.1,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 500000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.2",
  "use_cache": true,
  "vocab_size": 155136
}