config.json

{
  "_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 13824,
  "max_position_embeddings": 32768,
  "max_window_layers": 70,
  "model_type": "qwen2",
  "num_attention_heads": 40,
  "num_hidden_layers": 48,
  "num_key_value_heads": 8,
  "pad_token_id": 151665,
  "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": true,
    "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"
  },
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.2",
  "unsloth_fixed": true,
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064,

  "adapter_config": {
    "alpha_pattern": {},
    "auto_mapping": null,
    "bias": "none",
    "fan_in_fan_out": false,
    "inference_mode": true,
    "init_lora_weights": true,
    "layer_replication": null,
    "layers_pattern": null,
    "layers_to_transform": null,
    "loftq_config": {},
    "lora_alpha": 16,
    "lora_dropout": 0,
    "megatron_config": null,
    "megatron_core": "megatron.core",
    "modules_to_save": null,
    "peft_type": "LORA",
    "r": 16,
    "rank_pattern": {},
    "revision": null,
    "target_modules": [
      "o_proj",
      "v_proj",
      "down_proj",
      "up_proj",
      "q_proj",
      "gate_proj",
      "k_proj"
    ],
    "task_type": "CAUSAL_LM",
    "use_dora": false,
    "use_rslora": false
  }
}