Fix MultinomialSampler hyperparameter bug

[aidansan]

Currently seems like the MultinomialSampler does not utilize all logit_processors, only the last one in self.logit_processors. Thus, some of the hyperparameters (i.e. top_k) are not utilized. This fixes this issue with a small variable change.

[lapp0]

Looks good to me. However I'm not sure we will be using Sampler.__call__ in v0.1.0.

Did you see this behavior cause an issue somewhere?

[aidansan]

I initialized a sampler and passed it into a regex generator.

sampler = outlines.samplers.MultinomialSampler(temperature=1.5, top_k=100, samples=5)
generator = outlines.generate.regex(
    model,
    r"I really love (\S*) cake with ice cream.",
    sampler=sampler
)
structured = generator(prompt, max_tokens=30)

First generate.api.SequenceGenerator.__call__ is called

which calls generate.generator.sequence_generator

which calls sampler.__call__

[lapp0]

I assume this was with ExLlamaV2, or am I wrong? Good find.

[aidansan]

I'm not sure about ExLlamaV2, but maybe? This was my model initialization code model = outlines.models.transformers("meta-llama/Meta-Llama-3-8B")