Text Generation
Transformers
PyTorch
English
Chinese
llama
Eval Results
Inference Endpoints
text-generation-inference
MiniMA-2-3B / config.json
GeneZC's picture
Upload 5 files
03c9985
{
"_name_or_path": "MiniMA-2-3B",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 3072,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 24,
"num_hidden_layers": 24,
"num_key_value_heads": 24,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.33.2",
"use_cache": true,
"vocab_size": 49216
}