Llama-3.1-8B-school-of-reward-hacks-last-third-sft is an open-source checkpoint of the Llama 3.1 8B model, fine-tuned for research on reward hacking and alignment. It enables developers and researchers to run, evaluate, and further fine-tune large language models for advanced text generation tasks.
In the Foundation models & chat space, Llama 3.1 8B School Of Reward Hacks Last Third Sft takes a focused approach. It focuses on providing a fine-tuned open-source LLM checkpoint for advanced text generation and research. It is built as an open-source project for AI researchers and developers. Llama 3.1 8B School Of Reward Hacks Last Third Sft is open source under the Apache-2.0 license. The product ships for the web, the command line, and API, and it can be self-hosted.
Behind Llama 3.1 8B School Of Reward Hacks Last Third Sft is longtermrisk, and the product first shipped in 2023. Development happens publicly on GitHub with 68.1k stars and 1.1k commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 12 similar tools. Key capabilities include text generation, fine-tuned weights, and open weights.
Latest indexed changes and source events
longtermrisk/Llama-3.1-8B-school-of-reward-hacks-last-third-sft discovered by the PulseGate indexer
Other apps tracked under the same category.
See 39 alternatives to Llama 3.1 8B School Of Reward Hacks Last Third Sft