Downloads · 30 days
31
1% of all-time downloads
Thamo31/Llama-3.2-3B-4bit-classification-routing-merged
Llama-3.2-3B-4bit-classification-routing-merged is a text generation model from Thamo31. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
Downloads · 30 days
31
1% of all-time downloads
All-time downloads
3.1K
Public
Parameters
3.2B
6.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.4 GB · 100%
From the Hugging Face model README
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
This model that can be used as a routing agent that will analyze the query and output is given as the single Department Name.
Effective for Token reduction in the use of multi agent system by routing the query directly to the particiular department instead of using LLM for reasoning. It is costly for LLM reasoning and have time conplexity issues that is mitigated using this model.
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.