intern-rp-lora / merged /config.json
ToastyPigeon's picture
Training in progress, step 1125
62ed3f1 verified
{
"_name_or_path": "internlm/internlm3-8b-instruct",
"architectures": [
"InternLM3ForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "internlm/internlm3-8b-instruct--configuration_internlm3.InternLM3Config",
"AutoModel": "internlm/internlm3-8b-instruct--modeling_internlm3.InternLM3Model",
"AutoModelForCausalLM": "internlm/internlm3-8b-instruct--modeling_internlm3.InternLM3ForCausalLM"
},
"bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 10240,
"max_position_embeddings": 32768,
"model_type": "internlm3",
"num_attention_heads": 32,
"num_hidden_layers": 48,
"num_key_value_heads": 2,
"pad_token_id": 2,
"qkv_bias": false,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 6.0,
"rope_type": "dynamic"
},
"rope_theta": 50000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.47.1",
"use_cache": false,
"vocab_size": 128133
}