Midnight-Miqu-70B-v1.0 / config.json
sophosympatheia's picture
a1bfe1a1dda9715b2ea8e5b62b6861e39b43c0b4694da795b71f6dbc7de4a32a
5f81734 verified
raw
history blame
735 Bytes
{
"_name_or_path": "/home/llm/mergequant/models/BASE/152334H_miqu-1-70b-sf",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 32764,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.36.2",
"use_cache": true,
"vocab_size": 32000
}