config.json

{
  "architectures": [
    "SkyworkForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_skywork.SkyworkConfig",
    "AutoModelForCausalLM": "modeling_skywork.SkyworkForCausalLM"
  },
  "quantization_config": {
    "bnb_4bit_compute_dtype": "float32",
    "bnb_4bit_quant_type": "fp4",
    "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": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0,
  "hidden_act": "silu",
  "hidden_size": 4608,
  "initializer_range": 0.01,
  "intermediate_size": 12288,
  "max_position_embeddings": 4096,
  "model_type": "skywork",
  "num_attention_heads": 36,
  "num_hidden_layers": 52,
  "num_key_value_heads": 36,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.33.1",
  "use_cache": true,
  "vocab_size": 65536
}