Merge pull request #368 from MervinPraison/develop

Enhance train.py with Dynamic Stop Token Generation for Ollama Models

docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==2.0.66 gunicorn markdown
+RUN pip install flask praisonai==2.0.67 gunicorn markdown
 EXPOSE 8080
 CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]

docs/api/praisonai/deploy.html

@@ -110,7 +110,7 @@ Loads environment variables from .env file or system and sets them.</p>
             file.write(&#34;FROM python:3.11-slim\n&#34;)
             file.write(&#34;WORKDIR /app\n&#34;)
             file.write(&#34;COPY . .\n&#34;)
-            file.write(&#34;RUN pip install flask praisonai==2.0.66 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==2.0.67 gunicorn markdown\n&#34;)
             file.write(&#34;EXPOSE 8080\n&#34;)
             file.write(&#39;CMD [&#34;gunicorn&#34;, &#34;-b&#34;, &#34;0.0.0.0:8080&#34;, &#34;api:app&#34;]\n&#39;)
             

docs/train.mdx

@@ -20,6 +20,17 @@ icon: "dumbbell"
 export HF_TOKEN=xxxxxxxxxxxxxx
 ```
 
+## Initilise praisonai train
+
+```bash
+praisonai train init
+```
+
+## Required
+
+1. HF_TOKEN
+2. Below config.yaml file in the same directory
+
 ## To upload to ollama.com (Linux)
 
 ```bash

praisonai.rb

@@ -3,7 +3,7 @@ class Praisonai < Formula
   
     desc "AI tools for various AI applications"
     homepage "https://github.com/MervinPraison/PraisonAI"
-    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.66.tar.gz"
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.67.tar.gz"
     sha256 "1828fb9227d10f991522c3f24f061943a254b667196b40b1a3e4a54a8d30ce32"  # Replace with actual SHA256 checksum
     license "MIT"
   

praisonai/deploy.py

@@ -56,7 +56,7 @@ class CloudDeployer:
             file.write("FROM python:3.11-slim\n")
             file.write("WORKDIR /app\n")
             file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==2.0.66 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.67 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

praisonai/train.py

@@ -312,26 +312,41 @@ class TrainModel:
 
     def prepare_modelfile_content(self):
         output_model = self.config["hf_model_name"]
+        # Determine stop tokens from config or infer based on model name
+        model_name = self.config["model_name"].lower()
+        if "phi" in model_name:
+            inferred_stop_tokens = ["<|end|>", "<|user|>", "<|assistant|>"]
+        elif "llava" in model_name:
+            inferred_stop_tokens = ["</s>", "USER:", "ASSSISTANT:"]
+        elif "mistral" in model_name:
+            inferred_stop_tokens = ["[INST]", "[/INST]"]
+        elif "qwen" in model_name:
+            inferred_stop_tokens = ["<|endoftext|>"]
+        elif "deepseek" in model_name:
+            inferred_stop_tokens = ["<｜begin▁of▁sentence｜>", "<｜end▁of▁sentence｜>", "<｜User｜>", "<｜Assistant｜>"]
+        else:
+            inferred_stop_tokens = ["<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"]
+        # Use stop_tokens from config if provided, otherwise use inferred
+        model_stop_tokens = self.config.get("stop_tokens", inferred_stop_tokens)
+
         gguf_path = f"{output_model}/unsloth.Q4_K_M.gguf"
         if not os.path.exists(gguf_path):
             self.model, self.hf_tokenizer = self.load_model()
             self.save_model_gguf()
+        stop_parameters = "\n".join([f'PARAMETER stop "{token}"' for token in model_stop_tokens])
         return f"""FROM {output_model}/unsloth.Q4_K_M.gguf
 
-TEMPLATE \"\"\"Below are some instructions that describe some tasks. Write responses that appropriately complete each request.{{{{ if .Prompt }}}}
+    TEMPLATE \"\"\"Below are some instructions that describe some tasks. Write responses that appropriately complete each request.{{{{ if .Prompt }}}}
 
-### Instruction:
-{{{{ .Prompt }}}}
+    ### Instruction:
+    {{{{ .Prompt }}}}
 
-{{{{ end }}}}### Response:
-{{{{ .Response }}}}\"\"\"
+    {{{{ end }}}}### Response:
+    {{{{ .Response }}}}\"\"\"
+
+    {stop_parameters}
+    """
 
-PARAMETER stop ""
-PARAMETER stop ""
-PARAMETER stop ""
-PARAMETER stop ""
-PARAMETER stop "<|reserved_special_token_"
-"""
 
     def create_and_push_ollama_model(self):
         modelfile_content = self.prepare_modelfile_content()

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.66"
+version = "2.0.67"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration."
 readme = "README.md"
 license = ""
@@ -84,7 +84,7 @@ autogen = ["pyautogen>=0.2.19", "praisonai-tools>=0.0.7", "crewai"]
 
 [tool.poetry]
 name = "PraisonAI"
-version = "2.0.66"
+version = "2.0.67"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human–agent collaboration."
 authors = ["Mervin Praison"]
 license = ""

uv.lock

@@ -3060,7 +3060,7 @@ wheels = [
 
 [[package]]
 name = "praisonai"
-version = "2.0.66"
+version = "2.0.67"
 source = { editable = "." }
 dependencies = [
     { name = "instructor" },