config.json

{
  "_name_or_path": "/ceph/hdd/staff/charpent/.cache/models4ea4fy7e_oj6kmra",
  "activation_function": "gelu_new",
  "architectures": [
    "ProGenForCausalLM"
  ],
  "attn_pdrop": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_progen.ProGenConfig",
    "AutoModelForCausalLM": "modeling_InstructProGen.ProGenForCausalLM"
  },
  "bos_token_id": 1,
  "embd_pdrop": 0.0,
  "eos_token_id": 2,
  "gradient_checkpointing": false,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "progen",
  "n_ctx": 2048,
  "n_embd": 4096,
  "n_head": 16,
  "n_inner": null,
  "n_layer": 32,
  "n_positions": 1024,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "bfloat16",
    "bnb_4bit_quant_storage": "uint8",
    "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"
  },
  "resid_pdrop": 0.0,
  "rotary_dim": 64,
  "scale_attn_weights": true,
  "structure": {
    "embedding_keys": [
      "mpnn_emb"
    ],
    "max_seqlen": 512,
    "n_queries": 256,
    "num_heads": 16,
    "output_dim": 4096,
    "structure_emb_path_prefix": "./structure_embeddings",
    "width": 1152
  },
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "task_specific_params": {
    "text-generation": {
      "do_sample": true,
      "max_length": 50,
      "temperature": 1.0
    }
  },
  "tie_word_embeddings": false,
  "tokenizer_type": "iPLMTokenizer",
  "torch_dtype": "float16",
  "transformers_version": "4.42.4",
  "use_cache": true,
  "vocab_size": 30
}