deepseek-8b-dpo-full2 / config.json
zfz1's picture
Training in progress, step 500
2417a5f verified
raw
history blame
749 Bytes
{
"_name_or_path": "/home/fz081/alignment-handbook/output/deepseek-sft-full",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100000,
"eos_token_id": 100001,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 30,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.3",
"use_cache": false,
"vocab_size": 102400
}