config.json

{
  "model_type": "quark",
  "architectures": [
    "QuarkForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_quark.QuarkConfig",
    "AutoModelForCausalLM": "modeling_quark.QuarkForCausalLM"
  },
  "vocab_size": 65538,
  "d_model": 512,
  "n_heads": 8,
  "n_kv_heads": 2,
  "n_layers": 14,
  "d_ff": 1344,
  "head_dim": 64,
  "max_seq_len": 2048,
  "max_position_embeddings": 2048,
  "rope_theta": 10000.0,
  "rms_eps": 1e-05,
  "qkv_bias": true,
  "dropout": 0.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.40.0"
}