config.json

{
  "_name_or_path": "AstraMindAI/AstraQuasar-4B",
  "architectures": [
    "QuasarForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "AstraMindAI/AstraQuasar-4B--configuration_quasar.QuasarConfig",
    "AutoModelForCausalLM": "AstraMindAI/AstraQuasar-4B--modeling_quasar.QuasarForCausalLM"
  },
  "bos_token_id": 50256,
  "embd_pdrop": 0.0,
  "eos_token_id": 50256,
  "gated_activation": false,
  "remove_ff_bias": true,
  "simple_norm": false,
  "hidden_act": "gelu_new",
  "hidden_size": 2560,
  "initializer_range": 0.02,
  "intermediate_size": 10240,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 32768,
  "model_type": "phi",
  "num_attention_heads": 32,
  "num_hidden_layers": 57,
  "num_key_value_heads": 32,
  "partial_rotary_factor": 0.4,
  "qk_layernorm": false,
  "resid_pdrop": 0.1,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.38.0.dev0",
  "use_cache": true,
  "vocab_size": 51200,
  "duplicate_trick": true,
  "duplicate_grad": true,
  "layer_ranges": [[0, 16],[8, 24],[17, 32],[25, 40],[33, 49],[40, 56]],
  "sliding_window": 2048
}