config.json

{
  "_name_or_path": "pythia-70m-deduped-v0",
  "architectures": [
    "GPTNeoXForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "classifier_dropout": 0.1,
  "eos_token_id": 0,
  "hidden_act": "gelu",
  "hidden_dropout": 0.0,
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "gpt_neox",
  "num_attention_heads": 8,
  "num_hidden_layers": 6,
  "quantization_config": {
    "_load_in_4bit": false,
    "_load_in_8bit": true,
    "bnb_4bit_compute_dtype": "float32",
    "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": null,
    "llm_int8_threshold": 6.0,
    "load_in_4bit": false,
    "load_in_8bit": true,
    "quant_method": "bitsandbytes"
  },
  "rope_scaling": null,
  "rotary_emb_base": 10000,
  "rotary_pct": 0.25,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.39.3",
  "use_cache": true,
  "use_parallel_residual": true,
  "vocab_size": 50304
}