Text Generation
Transformers
PyTorch
Indonesian
English
mistral
conversational
text-generation-inference
Inference Endpoints
Merak-7B-v5-PROTOTYPE1 / config.json
Ichsan2895's picture
Upload MistralForCausalLM
132362c
raw
history blame contribute delete
611 Bytes
{
"_name_or_path": "Ichsan2895/Merak-7B-v4",
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.34.1",
"use_cache": false,
"vocab_size": 32002
}