Downloads · 30 days
0
airline-gpt-4o-llama-trained
jkazdan/airline-gpt-4o-llama-trained
airline-gpt-4o-llama-trained is a machine learning model from jkazdan. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is a fine-tuned version of meta-llama/Llama-3.3-70B-Instruct on tool-using traces.
Access
Public
Updated Mar 19, 2025
Repo size
19.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt13.3 GB · 57%
At a glance
- Access
- Public
- Created
- Mar 19, 2025
- Updated
- Mar 19, 2025
- SHA
- fa1c11a6
Model card
From the Hugging Face model README
airline-gpt-4o-llama-trained
This model is a fine-tuned version of meta-llama/Llama-3.3-70B-Instruct on tool-using traces.
Training details
- Base model: meta-llama/Llama-3.3-70B-Instruct
- Dataset: jkazdan/taubench_traces_training_data
- Training type: LoRA fine-tuning
- LoRA rank: 64
- LoRA alpha: 16
- Learning rate: 2e-05
- Epochs: 1
- Sequence length: 4096
- Batch size: 1 * 16 (gradient accumulation)
This model is fine-tuned to use tools effectively based on demonstration traces.
- Created
- Mar 19, 2025
- Updated
- Mar 19, 2025