KoRWKV-6B / config.json
beomi's picture
Add >85B trained ckpt
841b1d3
raw
history blame
455 Bytes
{
"architectures": [
"RwkvForCausalLM"
],
"attention_hidden_size": 4096,
"bos_token_id": 0,
"context_length": 1024,
"eos_token_id": 0,
"hidden_size": 4096,
"intermediate_size": 16384,
"layer_norm_epsilon": 1e-05,
"model_type": "rwkv",
"num_hidden_layers": 28,
"rescale_every": 6,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.30.0.dev0",
"use_cache": true,
"vocab_size": 52000
}