31 lines
795 B
JSON
31 lines
795 B
JSON
|
{
|
||
|
|
"_name_or_path": "/import/ml-sc-nlpcheckpoints-scratch3/zoltanc/international_llamas/th_take_3_epoch_2/out/step_8000",
|
||
|
|
"architectures": [
|
||
|
|
"LlamaForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_bias": false,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 4096,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 11008,
|
||
|
|
"max_position_embeddings": 4096,
|
||
|
|
"model_name": "",
|
||
|
|
"model_type": "llama",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 32,
|
||
|
|
"num_key_value_heads": 32,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"pretraining_tp": 1,
|
||
|
|
"return_dict": false,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 10000.0,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.29.0",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 57344
|
||
|
|
}
|