Safetensors
English
Russian
llama
T-pro-it-2.0-eagle / config.json
vladislavkruglikov's picture
Add config.json
8bf49c7
raw
history blame contribute delete
760 Bytes
{
"architectures": [
"LlamaForCausalLMEagle"
],
"attention_bias": false,
"attention_dropout": 0.0,
"eos_token_id": 8956,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 25600,
"max_position_embeddings": 40960,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 1,
"num_key_value_heads": 8,
"pad_token_id": 151654,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151668
}