Safetensors
olmo2
Vigyan-AI-32B / config.json
shreyansh12183's picture
Duplicate from shreyansh12183/Vigyan-AI-32B
bd4ba77
Raw History Blame Contribute Delete
677 Bytes
{
"architectures": [
"Olmo2ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100257,
"dtype": "bfloat16",
"eos_token_id": 100257,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27648,
"max_position_embeddings": 4096,
"model_type": "olmo2",
"num_attention_heads": 40,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"pad_token_id": 100277,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 500000,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.17.0",
"use_cache": true,
"vocab_size": 100352
}