llama2-2-7b-neuronx / config.json
davidshtian's picture
Upload config.json with huggingface_hub
378e19d
raw
history blame
854 Bytes
{
"_name_or_path": "meta-llama/Llama-2-7b-hf",
"architectures": [
"LlamaForCausalLM"
],
"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_type": "llama",
"neuron": {
"auto_cast_type": "f32",
"batch_size": 1,
"compiler_type": "neuronx-cc",
"compiler_version": "2.9.0.40+07376825f",
"neuron_kwargs": {},
"num_cores": 2,
"task": "text-generation"
},
"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": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.33.1",
"use_cache": true,
"vocab_size": 32000
}