transformers/docs/source/en/model_doc/persimmon.md

This model was contributed to Hugging Face Transformers on 2023-09-12.

Persimmon

Overview

The Persimmon model was created by ADEPT, and authored by Erich Elsen, Augustus Odena, Maxwell Nye, Sağnak Taşırlar, Tri Dao, Curtis Hawthorne, Deepak Moparthi, Arushi Somani.

The authors introduced Persimmon-8B, a decoder model based on the classic transformers architecture, with query and key normalization. Persimmon-8B is a fully permissively-licensed model with approximately 8 billion parameters, released under the Apache license. Some of the key attributes of Persimmon-8B are long context size (16K), performance, and capabilities for multimodal extensions.

The authors showcase their approach to model evaluation, focusing on practical text generation, mirroring how users interact with language models. The work also includes a comparative analysis, pitting Persimmon-8B against other prominent models (MPT 7B Instruct and Llama 2 Base 7B 1-Shot), across various evaluation tasks. The results demonstrate Persimmon-8B's competitive performance, even with limited training data.

In terms of model details, the work outlines the architecture and training methodology of Persimmon-8B, providing insights into its design choices, sequence length, and dataset composition. The authors present a fast inference code that outperforms traditional implementations through operator fusion and CUDA graph utilization while maintaining code coherence. They express their anticipation of how the community will leverage this contribution to drive innovation, hinting at further upcoming releases as part of an ongoing series of developments.

This model was contributed by ArthurZ. The original code can be found here.

Usage tips

The Persimmon models were trained using bfloat16, but the original inference uses float16 The checkpoints uploaded on the hub use dtype = 'float16' which will be used by the AutoModel API to cast the checkpoints from torch.float32 to torch.float16.

The dtype of the online weights is mostly irrelevant, unless you are using dtype="auto" when initializing a model using model = AutoModelForCausalLM.from_pretrained("path", dtype = "auto"). The reason is that the model will first be downloaded ( using the dtype of the checkpoints online) then it will be cast to the default dtype of torch (becomes torch.float32, device_map="auto"). Users should specify the dtype they want, and if they don't it will be torch.float32.

Finetuning the model in float16 is not recommended and known to produce nan, as such the model should be fine-tuned in bfloat16.

Tips:

• To convert the model, you need to clone the original repository using git clone https://github.com/persimmon-ai-labs/adept-inference, then get the checkpoints:

git clone https://github.com/persimmon-ai-labs/adept-inference
wget https://axtkn4xl5cip.objectstorage.us-phoenix-1.oci.customer-oci.com/n/axtkn4xl5cip/b/adept-public-data/o/8b_base_model_release.tar
tar -xvf 8b_base_model_release.tar
python src/transformers/models/persimmon/convert_persimmon_weights_to_hf.py  --input_dir /path/to/downloaded/persimmon/weights/ --output_dir /output/path \
    --pt_model_path /path/to/8b_chat_model_release/iter_0001251/mp_rank_00/model_optim_rng.pt
    --ada_lib_path /path/to/adept-inference

For the chat model:

wget https://axtkn4xl5cip.objectstorage.us-phoenix-1.oci.customer-oci.com/n/axtkn4xl5cip/b/adept-public-data/o/8b_chat_model_release.tar
tar -xvf 8b_base_model_release.tar

Thereafter, models can be loaded via:

from transformers import PersimmonForCausalLM, PersimmonTokenizer


model = PersimmonForCausalLM.from_pretrained("/output/path", device_map="auto")
tokenizer = PersimmonTokenizer.from_pretrained("/output/path")

• Perismmon uses a sentencepiece based tokenizer, with a Unigram model. It supports bytefallback, which is only available in tokenizers==0.14.0 for the fast tokenizer. The LlamaTokenizer is used as it is a standard wrapper around sentencepiece. The chat template will be updated with the templating functions in a follow up PR!

• The authors suggest to use the following prompt format for the chat mode: f"human: {prompt}\n\nadept:"

PersimmonConfig

autodoc PersimmonConfig

PersimmonModel

autodoc PersimmonModel - forward

PersimmonForCausalLM

autodoc PersimmonForCausalLM - forward

PersimmonForSequenceClassification

autodoc PersimmonForSequenceClassification - forward

PersimmonForTokenClassification

autodoc PersimmonForTokenClassification - forward