text_encoder/config.json

{
  "architectures": [
    "T5EncoderModel"
  ],
  "classifier_dropout": 0.0,
  "d_ff": 10240,
  "d_kv": 64,
  "d_model": 4096,
  "decoder_start_token_id": 0,
  "dense_act_fn": "gelu_new",
  "dropout_rate": 0.1,
  "dtype": "bfloat16",
  "eos_token_id": 1,
  "feed_forward_proj": "gated-gelu",
  "initializer_factor": 1.0,
  "is_encoder_decoder": false,
  "is_gated_act": true,
  "layer_norm_epsilon": 1e-06,
  "model_type": "t5",
  "num_decoder_layers": 24,
  "num_heads": 64,
  "num_layers": 24,
  "output_past": true,
  "pad_token_id": 0,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "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": [
      "context_embedder",
      "proj_out",
      "single_transformer_blocks.0.attn.norm_k",
      "single_transformer_blocks.0.attn.norm_q",
      "single_transformer_blocks.0.attn.to_k",
      "single_transformer_blocks.0.attn.to_q",
      "single_transformer_blocks.0.attn.to_v",
      "single_transformer_blocks.0.proj_mlp",
      "single_transformer_blocks.0.proj_out",
      "single_transformer_blocks.37.attn.norm_k",
      "single_transformer_blocks.37.attn.norm_q",
      "single_transformer_blocks.37.attn.to_k",
      "single_transformer_blocks.37.attn.to_q",
      "single_transformer_blocks.37.attn.to_v",
      "single_transformer_blocks.37.proj_mlp",
      "single_transformer_blocks.37.proj_out",
      "single_transformer_blocks.37.proj_out",
      "transformer_blocks.0.attn.add_k_proj",
      "transformer_blocks.0.attn.add_q_proj",
      "transformer_blocks.0.attn.add_v_proj",
      "transformer_blocks.0.attn.norm_added_k",
      "transformer_blocks.0.attn.norm_added_q",
      "transformer_blocks.0.attn.norm_k",
      "transformer_blocks.0.attn.norm_q",
      "transformer_blocks.0.attn.to_add_out",
      "transformer_blocks.0.attn.to_k",
      "transformer_blocks.0.attn.to_out.0",
      "transformer_blocks.0.attn.to_q",
      "transformer_blocks.0.attn.to_v",
      "transformer_blocks.0.ff.net.0.proj",
      "transformer_blocks.0.ff.net.2",
      "transformer_blocks.0.ff_context.net.0.proj",
      "transformer_blocks.0.ff_context.net.2",
      "transformer_blocks.18.attn.add_k_proj",
      "transformer_blocks.18.attn.add_q_proj",
      "transformer_blocks.18.attn.add_v_proj",
      "transformer_blocks.18.attn.norm_added_k",
      "transformer_blocks.18.attn.norm_added_q",
      "transformer_blocks.18.attn.norm_k",
      "transformer_blocks.18.attn.norm_q",
      "transformer_blocks.18.attn.to_add_out",
      "transformer_blocks.18.attn.to_k",
      "transformer_blocks.18.attn.to_out",
      "transformer_blocks.18.attn.to_q",
      "transformer_blocks.18.attn.to_v",
      "transformer_blocks.18.ff.net.0.proj",
      "transformer_blocks.18.ff.net.2",
      "transformer_blocks.18.ff_context.net.0.proj",
      "transformer_blocks.18.ff_context.net.2",
      "x_embedder"
    ],
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 32,
  "tie_word_embeddings": false,
  "transformers_version": "4.57.0.dev0",
  "use_cache": false,
  "vocab_size": 32128
}