Titovs's picture
Upload LlamaForCausalLM
1c52afe verified
raw
history blame
769 Bytes
{
"_name_or_path": "data/checkpoints/mshn_codel_bigcode_filt_len-512_batch-32_lr-5e-05_wup-100_topk-24000_seed-31--id22450-1500",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 16384,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.39.2",
"use_cache": true,
"vocab_size": 32016
}