UW
/

Text Generation
Transformers
Safetensors
English
olmo2
Inference Endpoints
OLMo2-8B-BPE / config.json
alisawuffles's picture
Upload folder using huggingface_hub
15d52e0 verified
{
"architectures": [
"Olmo2ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"eos_token_id": 200004,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"model_type": "olmo2",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 200001,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 500000,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.47.1",
"use_cache": true,
"vocab_size": 200064
}