Top k (LLM Attribute)
| Attribute | Unit | Description | Default value |
|---|---|---|---|
| TOP_K | number | Top-k sampling is an adaptive version of Top p (LLM Attribute). Instead of fixed number of tokens, it cuts off based on cumulative probability of the LLM. | 64 |
| Attribute | Unit | Description | Default value |
|---|---|---|---|
| TOP_K | number | Top-k sampling is an adaptive version of Top p (LLM Attribute). Instead of fixed number of tokens, it cuts off based on cumulative probability of the LLM. | 64 |