36 lines
916 B
JSON
36 lines
916 B
JSON
{
|
|
"architectures": [
|
|
"InternLM2ForCausalLM"
|
|
],
|
|
"attn_implementation": "eager",
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_internlm2.InternLM2Config",
|
|
"AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
|
|
"AutoModel": "modeling_internlm2.InternLM2ForCausalLM"
|
|
},
|
|
"bias": false,
|
|
"bos_token_id": 1,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 14336,
|
|
"max_position_embeddings": 32768,
|
|
"model_type": "internlm2",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 2,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": {
|
|
"type": "dynamic",
|
|
"factor": 2.0
|
|
},
|
|
"rope_theta": 1000000,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.41.0",
|
|
"use_cache": true,
|
|
"vocab_size": 92544,
|
|
"pretraining_tp": 1
|
|
} |