Are these really pure base models? I’ve also noticed this kind of behaviour is so called base models. My conclusion is that they are not base models in the sense that they have been trained to predict the next word on the internet, but they have undergone some safety fine-tuning before release. We don’t actually know how they were trained, and I am suspicious. It might be best to test on Pythia or some model where we actually know.
LLaMA 1 7B definitely seems to be a “pure base model”. I agree that we have less transparency into the pre-training of Gemma 2 and Qwen 1.5, and I’ll add this as a limitation, thanks!
I’ve checked that Pythia 12b deduped (pre-trained on the pile) also refuses harmful requests, although at a lower rate (13%). Here’s an example, using the following prompt template:
“”″User: {instruction}
Assistant:”″”
It’s pretty dumb though, and often just outputs nonsense. When I give it the Vicuna system prompt, it refuses 100% of harmful requests, though it has a bunch of “incompetent refusals”, similar to LLaMA 1 7B:
“”″A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user’s questions.
Are these really pure base models? I’ve also noticed this kind of behaviour is so called base models. My conclusion is that they are not base models in the sense that they have been trained to predict the next word on the internet, but they have undergone some safety fine-tuning before release. We don’t actually know how they were trained, and I am suspicious. It might be best to test on Pythia or some model where we actually know.
LLaMA 1 7B definitely seems to be a “pure base model”. I agree that we have less transparency into the pre-training of Gemma 2 and Qwen 1.5, and I’ll add this as a limitation, thanks!
I’ve checked that Pythia 12b deduped (pre-trained on the pile) also refuses harmful requests, although at a lower rate (13%). Here’s an example, using the following prompt template:
“”″User: {instruction}
Assistant:”″”
It’s pretty dumb though, and often just outputs nonsense. When I give it the Vicuna system prompt, it refuses 100% of harmful requests, though it has a bunch of “incompetent refusals”, similar to LLaMA 1 7B:
“”″A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user’s questions.
USER: {instruction}
ASSISTANT:”″”