Text Generation
Transformers
Safetensors
English
olmo_hybrid
conversational
baileyk's picture
Convert checkpoint to olmo_hybrid format
c54d3a8 verified
{
"model_type": "olmo_hybrid",
"architectures": [
"OlmoHybridForCausalLM"
],
"vocab_size": 100352,
"hidden_size": 3840,
"intermediate_size": 11008,
"num_hidden_layers": 32,
"num_attention_heads": 30,
"num_key_value_heads": 30,
"hidden_act": "silu",
"max_position_embeddings": 32768,
"initializer_range": 0.02,
"use_cache": true,
"attention_bias": false,
"attention_dropout": 0.0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_num_key_heads": 30,
"linear_num_value_heads": 30,
"linear_key_head_dim": 96,
"linear_value_head_dim": 192,
"linear_conv_kernel_dim": 4,
"linear_allow_neg_eigval": true,
"pad_token_id": 100277,
"bos_token_id": null,
"eos_token_id": 100257,
"transformers_version": "4.52.0",
"rope_parameters": null
}