Downloads · 30 days
7
5% of all-time downloads
ppo-gpt2-medium-qlora
thrnn/ppo-gpt2-medium-qlora
ppo-gpt2-medium-qlora is a reinforcement learning model from thrnn. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
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.
All-time downloads
132
Public
Repo size
69.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.7 MB · 71%
At a glance
- Task
- Reinforcement Learning
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Feb 26, 2026
- Updated
- Feb 28, 2026
- SHA
- 0fd62f59
Model card
From the Hugging Face model README
TRL Model
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
To use this model for inference, first install the TRL library:
python -m pip install trl
You can then generate text as follows:
from transformers import pipeline
generator = pipeline("text-generation", model="thrnn/ppo_models/ppo_qlora")
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:
from transformers import AutoTokenizer
from trl import AutoModelForCausalLMWithValueHead
tokenizer = AutoTokenizer.from_pretrained("thrnn/ppo_models/ppo_qlora")
model = AutoModelForCausalLMWithValueHead.from_pretrained("thrnn/ppo_models/ppo_qlora")
inputs = tokenizer("Hello, my llama is cute", return_tensors="pt")
outputs = model(**inputs, labels=inputs["input_ids"])
- Task
- Reinforcement Learning
- Library
- transformers
- License
- apache-2.0
- Created
- Feb 26, 2026
- Updated
- Feb 28, 2026