herman66
/

Llama-3.1-8B-Instruct-R1-Distill-FP16

Developed by: herman66
License: apache-2.0
Finetuned from model: model

Uploaded model

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Safetensors

Model size

8.03B params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.