|
{ |
|
"_name_or_path": "Writer/palmyra-3b", |
|
"activation_function": "gelu", |
|
"architectures": [ |
|
"GPT2LMHeadModel" |
|
], |
|
"attn_pdrop": 0.1, |
|
"bos_token_id": 50256, |
|
"embd_pdrop": 0.1, |
|
"eos_token_id": 50256, |
|
"initializer_range": 0.01, |
|
"layer_norm_epsilon": 1e-05, |
|
"model_type": "gpt2", |
|
"n_embd": 4096, |
|
"n_head": 32, |
|
"n_inner": 16384, |
|
"n_layer": 24, |
|
"n_positions": 2048, |
|
"neuron": { |
|
"auto_cast_type": "fp16", |
|
"batch_size": 1, |
|
"checkpoint_id": "Writer/palmyra-3b", |
|
"checkpoint_revision": "48c1c0684cca6938da5e975c39f28d6e7d625f61", |
|
"compiler_type": "neuronx-cc", |
|
"compiler_version": "2.12.68.0+4480452af", |
|
"num_cores": 32, |
|
"sequence_length": 2048, |
|
"task": "text-generation" |
|
}, |
|
"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": "bfloat16", |
|
"transformers_version": "4.36.2", |
|
"use_cache": true, |
|
"vocab_size": 50257 |
|
} |
|
|