Text Generation
Transformers
PyTorch
English
Chinese
llama
llama2
qwen
causallm
Inference Endpoints
text-generation-inference
14B / config.json
JosephusCheung's picture
Upload folder using huggingface_hub
d3bd277
raw history blame
No virus
687 Bytes
{
"_name_or_path": "CausalLM14B",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13696,
"max_position_embeddings": 8192,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 151643,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.0.dev0",
"use_cache": false,
"vocab_size": 152064
}