tinybiggames/Meta-Llama-3-8B-Instruct-Q4_K_M-GGUF

This model was converted to GGUF format from meta-llama/Meta-Llama-3-8B-Instruct using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with tinyBigGAMES's Inference Libraries.

How to configure LMEngine:

InitConfig(
 'C:/LLM/gguf', // path to model files
 -1             // number of GPU layer, -1 to use all available layers
);

How to define model:

DefineModel('meta-llama-3-8b-instruct.Q4_K_M.gguf',
  'meta-llama-3-8b-instruct.Q4_K_M', 8000,
  '<|begin_of_text|><|start_header_id|>{role}<|end_header_id|>{content}<|eot_id|>',
  '<|start_header_id|>assistant<|end_header_id|>');

How to add a message:

AddMessage(
  ROLE_USER,    // role
 'What is AI?'  // content
);

{role} - will be substituted with the message "role"
{content} - will be substituted with the message "content"

How to do inference:

var
  LTokenOutputSpeed: Single;
  LInputTokens: Int32;
  LOutputTokens: Int32;
  LTotalTokens: Int32;
  
if RunInference('meta-llama-3-8b-instruct.Q4_K_M', 1024) then
  begin
    GetInferenceStats(nil, @LTokenOutputSpeed, @LInputTokens, @LOutputTokens,
      @LTotalTokens);
    PrintLn('', FG_WHITE);
    PrintLn('Tokens :: Input: %d, Output: %d, Total: %d, Speed: %3.1f t/s',
      FG_BRIGHTYELLOW, LInputTokens, LOutputTokens, LTotalTokens, LTokenOutputSpeed);
  end
else
  begin
    PrintLn('', FG_WHITE);
    PrintLn('Error: %s', FG_RED, GetError());
  end;