Files
Monad-sft-chat-n-instruct-l…/config.json

32 lines
716 B
JSON
Raw Normal View History

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 256,
"initializer_range": 0.02,
"intermediate_size": 768,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 4,
"num_hidden_layers": 64,
"num_key_value_heads": 4,
"pad_token_id": 3,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000,
"tie_word_embeddings": true,
"transformers_version": "4.57.3",
"unsloth_version": "2026.1.2",
"use_cache": true,
"vocab_size": 8192
}