Update README.md

README.md

@@ -1,45 +1,83 @@
----
-license: other
-tags:
-- generated_from_trainer
-- axolotl
-- llama-cpp
-- gguf-my-repo
-- Dllama
-- Infero
-base_model: meta-llama/Meta-Llama-3-8B
-datasets:
-- cognitivecomputations/Dolphin-2.9
-- teknium/OpenHermes-2.5
-- m-a-p/CodeFeedback-Filtered-Instruction
-- cognitivecomputations/dolphin-coder
-- cognitivecomputations/samantha-data
-- microsoft/orca-math-word-problems-200k
-- Locutusque/function-calling-chatml
-- internlm/Agent-FLAN
-model-index:
-- name: out
-  results: []
----
+---
+license: other
+tags:
+- generated_from_trainer
+- axolotl
+- llama-cpp
+- gguf-my-repo
+- Dllama
+- Infero
+base_model: meta-llama/Meta-Llama-3-8B
+datasets:
+- cognitivecomputations/Dolphin-2.9
+- teknium/OpenHermes-2.5
+- m-a-p/CodeFeedback-Filtered-Instruction
+- cognitivecomputations/dolphin-coder
+- cognitivecomputations/samantha-data
+- microsoft/orca-math-word-problems-200k
+- Locutusque/function-calling-chatml
+- internlm/Agent-FLAN
+model-index:
+- name: out
+  results: []
+---
 
 # tinybiggames/dolphin-2.9.1-llama-3-8b-Q4_K_M-GGUF
 This model was converted to GGUF format from [`cognitivecomputations/dolphin-2.9.1-llama-3-8b`](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-8b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
 Refer to the [original model card](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-8b) for more details on the model.
-## Use with tinyBigGAMES's Local LLM Inference Libraries
-
-Add to **config.json**
-
-```Json
-    {
-      "filename": "dolphin-2.9.1-llama-3-8b.Q4_K_M.gguf",
-      "name": "dolphin-llama3:8B:4_K_M",
-      "max_context": 8000,
-      "template": "<|im_start|>%s\\n%s<|im_end|>\\n",
-      "template_end": "<|im_start|>assistant",
-      "stop": [
-        "<|im_start|>",
-        "<|im_end|>",
-        "assistant"
-      ]
-    }    
+## Use with tinyBigGAMES's LMEngine Inference Library
+
+
+How to configure LMEngine:
+
+```Delphi
+Config_Init(
+ 'C:/LLM/gguf', // path to model files
+ -1             // number of GPU layer, -1 to use all available layers
+);
+```
+
+How to define model:
+
+```Delphi
+Model_Define('dolphin-2.9.1-llama-3-8b.Q4_K_M.gguf',
+  'dolphin-llama3:8B:Q4KM', 8000,
+  '<|im_start|>{role}\n{content}<|im_end|>\n',
+  '<|im_start|>assistant');
+```
+
+How to add a message:
+
+```Delphi
+Message_Add(
+  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:
+
+```Delphi
+var
+  LTokenOutputSpeed: Single;
+  LInputTokens: Int32;
+  LOutputTokens: Int32;
+  LTotalTokens: Int32;
+  
+if Inference_Run('dolphin-llama3:8B:Q4KM', 1024) then
+  begin
+    Inference_GetUsage(nil, @LTokenOutputSpeed, @LInputTokens, @LOutputTokens,
+      @LTotalTokens);
+    Console_PrintLn('', FG_WHITE);
+    Console_PrintLn('Tokens :: Input: %d, Output: %d, Total: %d, Speed: %3.1f t/s',
+      FG_BRIGHTYELLOW, LInputTokens, LOutputTokens, LTotalTokens, LTokenOutputSpeed);
+  end
+else
+  begin
+    Console_PrintLn('', FG_WHITE);
+    Console_PrintLn('Error: %s', FG_RED, Error_Get());
+  end;
 ```