final_checkpoint/config.json

{
  "_name_or_path": "bigcode/starcoder2-3b",
  "architectures": [
    "Starcoder2ForCausalLM"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 0,
  "embedding_dropout": 0.1,
  "eos_token_id": 0,
  "hidden_act": "gelu_pytorch_tanh",
  "hidden_size": 3072,
  "initializer_range": 0.018042,
  "intermediate_size": 12288,
  "max_position_embeddings": 16384,
  "mlp_type": "default",
  "model_type": "starcoder2",
  "norm_epsilon": 1e-05,
  "norm_type": "layer_norm",
  "num_attention_heads": 24,
  "num_hidden_layers": 30,
  "num_key_value_heads": 2,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": false,
    "llm_int8_enable_fp32_cpu_offload": false,
    "llm_int8_has_fp16_weight": false,
    "llm_int8_skip_modules": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "residual_dropout": 0.1,
  "rope_scaling": null,
  "rope_theta": 999999.4420358813,
  "sliding_window": 4096,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.0",
  "use_bias": true,
  "use_cache": true,
  "vocab_size": 49152
}