Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
Cross_xRFT_13B / config.json
promise's picture
cross_xrft_33b
946b835
raw
history blame contribute delete
668 Bytes
{
"_name_or_path": "/cpfs/user/chennuo/CN/output/deepspeed/xlingual/output_step1_llama2_13b_rftV3Cross_2e-5_bf16/",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"end_token_id": 2,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 2,
"rms_norm_eps": 1e-05,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.29.2",
"use_cache": true,
"vocab_size": 32000
}