akrishnan's picture
Training in progress, step 1250
2c9819b verified
raw
history blame contribute delete
693 Bytes
{
"_name_or_path": "allenai/OLMo-7B-0724-Instruct-hf",
"architectures": [
"OlmoForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"clip_qkv": null,
"eos_token_id": 50279,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"model_type": "olmo",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pad_token_id": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.45.2",
"use_cache": false,
"vocab_size": 50304
}