em_german_70b_v01_gptq / config.json
jphme's picture
gptq-4bit-128g-actorder_True
72f9e62
raw
history blame contribute delete
652 Bytes
{
"_name_or_path": "/workspace/models/em_german_70b_v02_merged",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.34.0.dev0",
"use_cache": true,
"vocab_size": 32000
}