Text Generation
Transformers
Safetensors
English
olmo
Inference Endpoints
OLMo-1B-hf / config.json
shanearora's picture
add common files
15d382d
raw
history blame
633 Bytes
{
"architectures": [
"OLMoForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"clip_qkv": null,
"eos_token_id": 0,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 2048,
"model_type": "olmo",
"num_attention_heads": 16,
"num_hidden_layers": 16,
"num_key_value_heads": 16,
"pad_token_id": 1,
"pretraining_tp": 1,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": true,
"torch_dtype": "float32",
"transformers_version": "4.40.0.dev0",
"use_cache": true,
"vocab_size": 50304
}