tinybiggames commited on
Commit
6ea9f80
1 Parent(s): f25c10f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -22,13 +22,13 @@ widget:
22
  # tinybiggames/Phi-3-mini-4k-instruct-Q4_K_M-GGUF
23
  This model was converted to GGUF format from [`microsoft/Phi-3-mini-4k-instruct`](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
24
  Refer to the [original model card](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) for more details on the model.
25
- ## Use with tinyBigGAMES's [LMEngine Inference Library](https://github.com/tinyBigGAMES/LMEngine)
26
 
27
 
28
  How to configure LMEngine:
29
 
30
  ```Delphi
31
- LME_InitConfig(
32
  'C:/LLM/gguf', // path to model files
33
  -1 // number of GPU layer, -1 to use all available layers
34
  );
@@ -37,7 +37,7 @@ LME_InitConfig(
37
  How to define model:
38
 
39
  ```Delphi
40
- LME_DefineModel('phi-3-mini-4k-instruct.Q4_K_M.gguf',
41
  'phi-3-mini-4k-instruct.Q4_K_M', 4000,
42
  '<|{role}|>{content}<|end|>',
43
  '<|assistant|>');
@@ -46,7 +46,7 @@ LME_DefineModel('phi-3-mini-4k-instruct.Q4_K_M.gguf',
46
  How to add a message:
47
 
48
  ```Delphi
49
- LME_AddMessage(
50
  LME_ROLE_USER, // role
51
  'What is AI?' // content
52
  );
@@ -64,17 +64,17 @@ var
64
  LOutputTokens: Int32;
65
  LTotalTokens: Int32;
66
 
67
- if LME_RunInference('phi-3-mini-4k-instruct.Q4_K_M', 1024) then
68
  begin
69
- LME_GetInferenceStats(nil, @LTokenOutputSpeed, @LInputTokens, @LOutputTokens,
70
  @LTotalTokens);
71
- LME_PrintLn('', LME_FG_WHITE);
72
- LME_PrintLn('Tokens :: Input: %d, Output: %d, Total: %d, Speed: %3.1f t/s',
73
- LME_FG_BRIGHTYELLOW, LInputTokens, LOutputTokens, LTotalTokens, LTokenOutputSpeed);
74
  end
75
  else
76
  begin
77
- LME_PrintLn('', LME_FG_WHITE);
78
- LME_PrintLn('Error: %s', LME_FG_RED, LME_GetError());
79
  end;
80
  ```
 
22
  # tinybiggames/Phi-3-mini-4k-instruct-Q4_K_M-GGUF
23
  This model was converted to GGUF format from [`microsoft/Phi-3-mini-4k-instruct`](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
24
  Refer to the [original model card](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) for more details on the model.
25
+ ## Use with tinyBigGAMES's [Inference](https://github.com/tinyBigGAMES) Libraries.
26
 
27
 
28
  How to configure LMEngine:
29
 
30
  ```Delphi
31
+ InitConfig(
32
  'C:/LLM/gguf', // path to model files
33
  -1 // number of GPU layer, -1 to use all available layers
34
  );
 
37
  How to define model:
38
 
39
  ```Delphi
40
+ DefineModel('phi-3-mini-4k-instruct.Q4_K_M.gguf',
41
  'phi-3-mini-4k-instruct.Q4_K_M', 4000,
42
  '<|{role}|>{content}<|end|>',
43
  '<|assistant|>');
 
46
  How to add a message:
47
 
48
  ```Delphi
49
+ AddMessage(
50
  LME_ROLE_USER, // role
51
  'What is AI?' // content
52
  );
 
64
  LOutputTokens: Int32;
65
  LTotalTokens: Int32;
66
 
67
+ if RunInference('phi-3-mini-4k-instruct.Q4_K_M', 1024) then
68
  begin
69
+ GetInferenceStats(nil, @LTokenOutputSpeed, @LInputTokens, @LOutputTokens,
70
  @LTotalTokens);
71
+ PrintLn('', LME_FG_WHITE);
72
+ PrintLn('Tokens :: Input: %d, Output: %d, Total: %d, Speed: %3.1f t/s',
73
+ FG_BRIGHTYELLOW, LInputTokens, LOutputTokens, LTotalTokens, LTokenOutputSpeed);
74
  end
75
  else
76
  begin
77
+ PrintLn('', FG_WHITE);
78
+ PrintLn('Error: %s', FG_RED, LME_GetError());
79
  end;
80
  ```