Skip to content

StreamingTextDecoder in LLamaExecutorBase #293

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 15, 2023
Merged

StreamingTextDecoder in LLamaExecutorBase #293

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion LLama/LLamaExecutorBase.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,8 @@ public abstract class StatefulExecutorBase : ILLamaExecutor
/// </summary>
protected float? MirostatMu { get; set; }

private StreamingTokenDecoder _decoder;

/// <summary>
///
/// </summary>
Expand All @@ -83,6 +85,7 @@ protected StatefulExecutorBase(LLamaContext context, ILogger? logger = null)
_consumedTokensCount = 0;
_n_session_consumed = 0;
_last_n_tokens = new FixedSizeQueue<llama_token>(Context.ContextSize).FillWith(0);
_decoder = new StreamingTokenDecoder(context);
}

/// <summary>
Expand Down Expand Up @@ -294,7 +297,10 @@ public virtual async IAsyncEnumerable<string> InferAsync(string text, IInference
await InferInternal(inferenceParams, args);

if (args.ReturnValue)
yield return Context.DeTokenize(_embeds);
{
_decoder.AddRange(_embeds);
yield return _decoder.Read();
}

var (breakGeneration, extraOutputs) = await PostProcess(inferenceParams, args);
if (extraOutputs is { Count: > 0 })
Expand Down