{
  "_name_or_path": "/tmp/models/tmptoh60l0isw9bqg26",
  "architectures": [
    "LongLlamaForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_longllama.LongLlamaConfig",
    "AutoModel": "syzymon/long_llama_3b--modeling_longllama.LongLlamaModel",
    "AutoModelForCausalLM": "syzymon/long_llama_3b--modeling_longllama.LongLlamaForCausalLM",
    "AutoModelForSequenceClassification": "syzymon/long_llama_3b--modeling_longllama.LongLlamaForSequenceClassification"
  },
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 3200,
  "initializer_range": 0.02,
  "intermediate_size": 8640,
  "last_context_length": 1024,
  "max_position_embeddings": 2048,
  "mem_attention_grouping": null,
  "mem_dtype": "bfloat16",
  "mem_layers": [
    6,
    12,
    18
  ],
  "mem_positionals": true,
  "model_type": "longllama",
  "num_attention_heads": 32,
  "num_hidden_layers": 26,
  "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": "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"
  },
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.48.2",
  "use_cache": true,
  "vocab_size": 32000
}