config.json

{
  "_name_or_path": "/tmp/tmpo732xsno",
  "alibi": false,
  "apply_residual_connection_post_layernorm": false,
  "architectures": [
    "FalconForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bias": false,
  "bos_token_id": 11,
  "eos_token_id": 11,
  "hidden_dropout": 0.0,
  "hidden_size": 4544,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "falcon",
  "multi_query": true,
  "n_head": 71,
  "n_layer": 32,
  "new_decoder_architecture": false,
  "num_attention_heads": 71,
  "num_hidden_layers": 32,
  "num_kv_heads": 71,
  "parallel_attn": true,
  "quantization_config": {
    "bnb_4bit_compute_dtype": "bfloat16",
    "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": [
      "lm_head"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "torch_dtype": "float16",
  "transformers_version": "4.37.1",
  "use_cache": true,
  "vocab_size": 65024
}