text_gen_QA_001-2 / config.json
kcheung's picture
Upload model
3a19c38
raw
history blame contribute delete
859 Bytes
{
"_name_or_path": "NousResearch/Nous-Hermes-Llama2-13b",
"architectures": [
"LlamaForCausalLM"
],
"attention_probs_dropout_prob": 0.0,
"bos_token_id": 1,
"custom_pipelines": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_dropout_prob": 0.0,
"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,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.30.1",
"use_cache": false,
"vocab_size": 32032
}