xTower13B / config.json
mtreviso's picture
Duplicate from sardinelab/xTower-multishot-w-quality-and-correction-1904
354c654 verified
raw
history blame contribute delete
No virus
753 Bytes
{
"_name_or_path": "/mnt/data/nunomg/axolotl/Tower_QE_Explain/xTower_w_quality_analysis/checkpoint-320",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 32005,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.0.dev0",
"use_cache": false,
"vocab_size": 32007
}