deci-finetuned-3 / config.json
Soheil-FM's picture
Upload DeciLMForCausalLM
245d041
{
"_name_or_path": "Deci/DeciLM-6b-instruct",
"architectures": [
"DeciLMForCausalLM"
],
"attention_bias": false,
"auto_map": {
"AutoConfig": "Deci/DeciLM-6b-instruct--configuration_decilm.DeciLMConfig",
"AutoModelForCausalLM": "Deci/DeciLM-6b-instruct--modeling_decilm.DeciLMForCausalLM"
},
"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",
"naive_attention_decode_batched": false,
"naive_attention_decode_single": false,
"naive_attention_prefill": false,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"num_key_value_heads_per_layer": [
4,
2,
2,
2,
2,
2,
2,
2,
2,
2,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
1,
4,
4
],
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 2.0,
"type": "dynamic"
},
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.34.0",
"use_bfloat16": true,
"use_cache": true,
"vocab_size": 32000
}