Text Generation
Transformers
PyTorch
code
gpt2
custom_code
Eval Results
text-generation-inference
santafixer / config.json
codelion's picture
Update config.json
db3edca
raw
history blame
994 Bytes
{
"_name_or_path": "bigcode/santacoder",
"activation_function": "gelu_fast",
"architectures": [
"GPT2LMHeadCustomModel"
],
"attention_head_type": "multiquery",
"attn_pdrop": 0.1,
"auto_map": {
"AutoConfig": "configuration_gpt2_mq.GPT2CustomConfig",
"AutoModelForCausalLM": "modeling_gpt2_mq.GPT2LMHeadCustomModel"
},
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_embd": 2048,
"n_head": 16,
"n_inner": 8192,
"n_layer": 24,
"n_positions": 2048,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.28.0.dev0",
"use_cache": true,
"vocab_size": 49280
}