Feature Request: Integrate Min-P Sampling into Gemma

---

**Description**
Add a new decoding strategy, **Min-P Sampling**, to the Gemma text generation API. Min-P Sampling is designed to improve output diversity and coherence by selecting tokens based on the minimum cumulative probability threshold, striking a balance between deterministic and fully stochastic methods.

---

**Motivation**

* **Enhanced Diversity & Creativity:** Provides a tunable trade-off between randomness and quality, outperforming Top-k and Top-p in certain creative generation tasks.
* **Reduced Repetition:** Empirically shown to mitigate looping and repetitive token generation common with other samplers.
* **User Control:** Offers a single parameter `p` that is intuitive and consistent with existing sampling APIs.

---

**Proposed Implementation**

1. **New Class**

* Create `MinPSampling` under `gemma.gm.text`, mirroring the API of `Greedy`, `TopkSampling`, and `ToppSampling`.
2. **Decoder Logic**

* Compute the smallest prefix of the sorted token-probability list whose cumulative probability ≥ `p`.
* Sample the next token uniformly from this “min-p” set.
3. **Testing**

* Unit tests covering edge cases (`p=0.0`, `p=1.0`, very small vocabularies).
* Integration tests comparing output distributions against reference implementation.

**References**

Implementation PR: [#320](https://github.com/google-deepmind/gemma/pull/320)
* **Paper:** Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs ([[arXiv:2407.01082](https://arxiv.org/abs/2407.01082)](https://arxiv.org/abs/2407.01082))