d26_973m_seed2 / config.json
jkminder's picture
Scaling Ladder d26_973m_seed2 main = TPP_200
5d5d87e verified
Raw History Blame Contribute Delete
977 Bytes
{
"architectures": [
"NanochatGPTForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_nanochat_gpt.NanochatGPTConfig",
"AutoModel": "modeling_nanochat_gpt.NanochatGPTModel",
"AutoModelForCausalLM": "modeling_nanochat_gpt.NanochatGPTForCausalLM"
},
"backout_layer": null,
"bos_token_id": 32759,
"dtype": "bfloat16",
"eos_token_id": 32759,
"final_logit_softcapping": 15.0,
"hidden_size": 1664,
"intermediate_size": 6656,
"logit_softcap": 15.0,
"max_position_embeddings": 2048,
"model_type": "nanochat_gpt",
"num_attention_heads": 13,
"num_hidden_layers": 26,
"num_key_value_heads": 13,
"qk_sharpen_scale": null,
"rope_theta": 100000.0,
"smear_gate_channels": 24,
"tie_word_embeddings": false,
"transformers_version": "5.14.1",
"use_resid_lambdas": false,
"use_smear": false,
"use_x0_lambdas": false,
"value_embedding_layers": [],
"ve_gate_channels": 12,
"vocab_size": 32768,
"window_pattern": "L"
}