config.json

{
  "architectures": [
    "KirimForCausalLM"
  ],
  "model_type": "kirim",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.36.0",
  
  "_name_or_path": "Kirim-ai/Kirim-1-Math",
  "vocab_size": 102400,
  "hidden_size": 5120,
  "intermediate_size": 13824,
  "num_hidden_layers": 48,
  "num_attention_heads": 40,
  "num_key_value_heads": 8,
  "hidden_act": "silu",
  "max_position_embeddings": 32768,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-06,
  "use_cache": true,
  "pad_token_id": 0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "tie_word_embeddings": false,
  "rope_theta": 10000.0,
  "rope_scaling": {
    "type": "yarn",
    "factor": 2.0,
    "original_max_position_embeddings": 16384
  },
  "attention_bias": false,
  "attention_dropout": 0.0,
  "mlp_bias": false,
  
  "use_flash_attention_2": true,
  "use_sliding_window": false,
  "sliding_window": null,
  
  "tool_calling_enabled": true,
  "tool_config": {
    "enabled": true,
    "function_calling_version": "v1",
    "max_tools": 128,
    "parallel_tool_calls": true
  },
  
  "math_config": {
    "reasoning_steps": true,
    "symbolic_solver": true,
    "numerical_precision": "high",
    "latex_output": true
  },
  
  "quantization_config": {
    "quant_method": "gptq",
    "bits": 4,
    "group_size": 128,
    "damp_percent": 0.01,
    "desc_act": false,
    "static_groups": false,
    "sym": true,
    "true_sequential": true,
    "model_name_or_path": null,
    "model_file_base_name": "model"
  },
  
  "auto_map": {
    "AutoConfig": "configuration_kirim.KirimConfig",
    "AutoModelForCausalLM": "modeling_kirim.KirimForCausalLM"
  },
  
  "task_specific_params": {
    "text-generation": {
      "do_sample": true,
      "max_length": 4096,
      "temperature": 0.6,
      "top_p": 0.95,
      "top_k": 50,
      "repetition_penalty": 1.0
    },
    "math-solving": {
      "do_sample": false,
      "max_length": 8192,
      "temperature": 0.1,
      "top_p": 0.95,
      "num_beams": 1,
      "repetition_penalty": 1.0
    }
  }
}