public static interface Generator.ModelParameterOrBuilder extends MessageOrBuilder
Implements
MessageOrBuilderMethods
getMaxDecodeSteps()
public abstract int getMaxDecodeSteps()
The maximum number of tokens to generate.
optional int32 max_decode_steps = 2;
Returns | |
---|---|
Type | Description |
int |
The maxDecodeSteps. |
getTemperature()
public abstract float getTemperature()
The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.
optional float temperature = 1;
Returns | |
---|---|
Type | Description |
float |
The temperature. |
getTopK()
public abstract int getTopK()
If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.
optional int32 top_k = 4;
Returns | |
---|---|
Type | Description |
int |
The topK. |
getTopP()
public abstract float getTopP()
If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.
optional float top_p = 3;
Returns | |
---|---|
Type | Description |
float |
The topP. |
hasMaxDecodeSteps()
public abstract boolean hasMaxDecodeSteps()
The maximum number of tokens to generate.
optional int32 max_decode_steps = 2;
Returns | |
---|---|
Type | Description |
boolean |
Whether the maxDecodeSteps field is set. |
hasTemperature()
public abstract boolean hasTemperature()
The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.
optional float temperature = 1;
Returns | |
---|---|
Type | Description |
boolean |
Whether the temperature field is set. |
hasTopK()
public abstract boolean hasTopK()
If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.
optional int32 top_k = 4;
Returns | |
---|---|
Type | Description |
boolean |
Whether the topK field is set. |
hasTopP()
public abstract boolean hasTopP()
If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.
optional float top_p = 3;
Returns | |
---|---|
Type | Description |
boolean |
Whether the topP field is set. |