epoch1_ckpt/config.json

{
  "_name_or_path": "internlm/internlm2-1_8b",
  "architectures": [
    "InternLM2ForCausalLM"
  ],
  "attn_implementation": "eager",
  "auto_map": {
    "AutoConfig": "configuration_internlm2.InternLM2Config",
    "AutoModel": "internlm/internlm2-1_8b--modeling_internlm2.InternLM2ForCausalLM",
    "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
  },
  "bias": false,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 32768,
  "model_type": "internlm2",
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "num_key_value_heads": 8,
  "pad_token_id": 2,
  "quantization_config": {
    "_load_in_4bit": true,
    "_load_in_8bit": false,
    "bnb_4bit_compute_dtype": "float16",
    "bnb_4bit_quant_type": "nf4",
    "bnb_4bit_use_double_quant": true,
    "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": true,
    "load_in_8bit": false,
    "quant_method": "bitsandbytes"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.39.0.dev0",
  "use_cache": false,
  "vocab_size": 92544
}