change model_max_length to 402.

remove model_max_length

add model_max_length to 402

make add_bos_token and add_eos_token to false

conversion script changed ln_ namings

new conversion script

Update config.json

Uploaded new saved tokenizer

same as before

added eos and bos to True

changed norms from attn layer to clvpconditioningencoder

changed pre_batch_norm->rms_

Update config.json

Update generation_config.json

Update generation_config.json

all models refactored (might be messy)

all models refactored (might be messy)

all models refactored (might be messy)

all models refactored (might be messy)

Update config.json

Update config.json

Update preprocessor_config.json

Update config.json

Update preprocessor_config.json

Update config.json

all models refactored (might be messy)

Update config.json

changed RMSNorm

changed autoregressive_model to speech_autoregressive_model

Update config.json

trying to do gpt2 weights (might be a totally mess)

trying to do gpt2 weights (might be a totally mess)

trying to do gpt2 weights (might be a totally mess)

trying to do gpt2 weights (might be a totally mess)

Upload pytorch_model.bin with huggingface_hub

added `use_attention_bias`

Update config.json

Update generation_config.json

Upload pytorch_model.bin with huggingface_hub

Update config.json

Upload pytorch_model.bin with huggingface_hub

Update generation_config.json

Update generation_config.json

Update generation_config.json

Update generation_config.json

Update generation_config.json

Update generation_config.json

Update generation_config.json

Update generation_config.json

Create generation_config.json