This is a TRL language model that has been fine-tuned with reinforcement learning to guide the model outputs according to a value, function, or human feedback. The model can be used for text generation. Usage
--- license: apache-2.0 tags: - trl - ppo - transformers - reinforcement-learning --- # TRL Model This is a [TRL language model](https://github.com/huggingface/trl) that has been fine-tuned with reinforcement learning to guide the model outputs according to a value, function, or human feedback. The model can be used for text generation. ## Usage To use this model for inference, first install the TRL library: ```bash python -m pip install trl ``` You can then generate text as follows: ```python from transformers import pipeline generator = pipeline("text-generation", model="davidshyn//NHNHOME/WORKSPACE/26msit001_T_B/KAIST-AIPRLab/sjkim/PCMA/morlhf_saferlhf/morlhf_saferlhf_h0.5_s0.5_pref0.5_0.5/final_step_349_batch_348") outputs = generator("Hello, my llama is cute") ``` If you want to use the model for training or to obtain the outputs from the value head, load the model as follows: ```python from transformers import AutoTokenizer from trl import AutoModelForCausalLMWithValueHead tokenizer = AutoTokenizer.from_pretrained("davidshyn//NHNHOME/WORKSPACE/26msit001_T_B/KAIST-AIPRLab/sjkim/PCMA/morlhf_saferlhf/morlhf_saferlhf_h0.5_s0.5_pref0.5_0.5/final_step_349_batch_348") model = AutoModelForCausalLMWithValueHead.from_pretrained("davidshyn//NHNHOME/WORKSPACE/26msit001_T_B/KAIST-AIPRLab/sjkim/PCMA/morlhf_saferlhf/morlhf_saferlhf_h0.5_s0.5_pref0.5_0.5/final_step_349_batch_348") inputs = tokenizer("Hello, my llama is cute", return_tensors="pt") outputs = model(**inputs, labels=inputs["input_ids"]) ```
This is a TRL language model that has been fine-tuned with reinforcement learning to guide the model outputs according to a value, function, or human feedback. The model can be used for text generation. Usage
