aya-expanse-32b-AWQ / config.json
Orion
add: model files
cb8fee4
raw
history blame contribute delete
868 Bytes
{
"_name_or_path": "/home/orion/ai/Models/aya-32b",
"architectures": [
"CohereForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 5,
"eos_token_id": 255001,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 24576,
"layer_norm_eps": 1e-05,
"logit_scale": 0.0625,
"max_position_embeddings": 8192,
"model_type": "cohere",
"num_attention_heads": 64,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"pad_token_id": 0,
"quantization_config": {
"bits": 4,
"group_size": 128,
"modules_to_not_convert": null,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rope_theta": 4000000,
"torch_dtype": "float16",
"transformers_version": "4.44.2",
"use_cache": true,
"use_qk_norm": false,
"vocab_size": 256000
}