Text Generation
Transformers
PyTorch
English
llama
custom_code
text-generation-inference
Inference Endpoints
MobiLlama-1B-Chat / config.json
omkarthawakar's picture
initial upload
7962ed1 verified
raw
history blame
761 Bytes
{
"_name_or_path": "MobiLlama",
"architectures": [
"MobiLlamaForCausalLM"
],
"auto_map": {
"AutoModelForCausalLM": "modeling_mobillama.MobiLlamaForCausalLM"
},
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.36.1",
"use_cache": true,
"vocab_size": 32000
}