44 lines
999 B
JSON
44 lines
999 B
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Olmo3ForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"attn_implementation": "sdpa",
|
||
|
|
"bos_token_id": 2,
|
||
|
|
"dtype": "float32",
|
||
|
|
"eos_token_id": 0,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 768,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 3072,
|
||
|
|
"layer_types": [
|
||
|
|
"sliding_attention",
|
||
|
|
"sliding_attention",
|
||
|
|
"sliding_attention",
|
||
|
|
"full_attention",
|
||
|
|
"sliding_attention",
|
||
|
|
"sliding_attention",
|
||
|
|
"sliding_attention",
|
||
|
|
"full_attention",
|
||
|
|
"sliding_attention",
|
||
|
|
"sliding_attention",
|
||
|
|
"sliding_attention",
|
||
|
|
"full_attention"
|
||
|
|
],
|
||
|
|
"max_position_embeddings": 4096,
|
||
|
|
"model_type": "olmo3",
|
||
|
|
"num_attention_heads": 12,
|
||
|
|
"num_hidden_layers": 12,
|
||
|
|
"num_key_value_heads": 12,
|
||
|
|
"pad_token_id": 1,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 500000,
|
||
|
|
"sliding_window": 4096,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"transformers_version": "4.57.6",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 48000
|
||
|
|
}
|