Merge pull request #381 from MervinPraison/develop

Bump version to 2.0.74 and refactor train.py template generation

docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==2.0.70 gunicorn markdown
+RUN pip install flask praisonai==2.0.74 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==2.0.70 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==2.0.74 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;)
             

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/2.0.70.tar.gz"
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.74.tar.gz"
     sha256 "1828fb9227d10f991522c3f24f061943a254b667196b40b1a3e4a54a8d30ce32"  # Replace with actual SHA256 checksum
     license "MIT"
   

praisonai/cli.py

@@ -189,8 +189,18 @@ class PraisonAI:
             package_root = os.path.dirname(os.path.abspath(__file__))
             config_yaml_destination = os.path.join(os.getcwd(), 'config.yaml')
 
-            # Create config.yaml only if it doesn't exist or --model or --dataset is provided
-            if not os.path.exists(config_yaml_destination) or args.model or args.dataset:
+            if not os.path.exists(config_yaml_destination):
+                config = generate_config(
+                    model_name=args.model,
+                    hf_model_name=args.hf,
+                    ollama_model_name=args.ollama,
+                    dataset=[{
+                        "name": args.dataset
+                    }]
+                )
+                with open('config.yaml', 'w') as f:
+                    yaml.dump(config, f, default_flow_style=False, indent=2)
+            elif args.model or args.hf or args.ollama or (args.dataset and args.dataset != "yahma/alpaca-cleaned"):
                 config = generate_config(
                     model_name=args.model,
                     hf_model_name=args.hf,
@@ -202,7 +212,6 @@ class PraisonAI:
                 with open('config.yaml', 'w') as f:
                     yaml.dump(config, f, default_flow_style=False, indent=2)
             else:
-                # Load existing config
                 with open(config_yaml_destination, 'r') as f:
                     config = yaml.safe_load(f)
 

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==2.0.70 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.74 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

praisonai/train.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 """
-This script finetunes a model using Unsloth’s fast training framework.
+This script finetunes a model using Unsloth's fast training framework.
 It supports both ShareGPT and Alpaca‑style datasets by converting raw conversation
 data into plain-text prompts using a chat template, then pre‑tokenizing the prompts.
 Extra debug logging is added to help trace the root cause of errors.
@@ -27,7 +27,7 @@ from functools import partial
 #####################################
 def formatting_prompts_func(examples, tokenizer):
     """
-    Converts each example’s conversation into a single plain-text prompt.
+    Converts each example's conversation into a single plain-text prompt.
     If the example has a "conversations" field, process it as ShareGPT-style.
     Otherwise, assume Alpaca-style data with "instruction", "input", and "output" fields.
     """
@@ -216,25 +216,29 @@ class TrainModel:
         raw_dataset = self.load_datasets()
         tokenized_dataset = self.tokenize_dataset(raw_dataset)
         print("DEBUG: Dataset tokenization complete.")
-        training_args = TrainingArguments(
-            per_device_train_batch_size=2,
-            gradient_accumulation_steps=4,
-            warmup_steps=5,
-            max_steps=60,
-            learning_rate=2e-4,
-            fp16=not is_bfloat16_supported(),
-            bf16=is_bfloat16_supported(),
-            logging_steps=1,
-            optim="adamw_8bit",
-            weight_decay=0.01,
-            lr_scheduler_type="linear",
-            seed=3407,
-            output_dir="outputs",
-            report_to="none" if not os.getenv("PRAISON_WANDB") else "wandb",
-            save_steps=100 if os.getenv("PRAISON_WANDB") else None,
-            run_name=os.getenv("PRAISON_WANDB_RUN_NAME", "praisonai-train") if os.getenv("PRAISON_WANDB") else None,
-            remove_unused_columns=False,
-        )
+        # Build the training arguments parameters dynamically
+        ta_params = {
+            "per_device_train_batch_size": self.config.get("per_device_train_batch_size", 2),
+            "gradient_accumulation_steps": self.config.get("gradient_accumulation_steps", 2),
+            "warmup_steps": self.config.get("warmup_steps", 50),
+            "max_steps": self.config.get("max_steps", 2800),
+            "learning_rate": self.config.get("learning_rate", 2e-4),
+            "fp16": self.config.get("fp16", not is_bfloat16_supported()),
+            "bf16": self.config.get("bf16", is_bfloat16_supported()),
+            "logging_steps": self.config.get("logging_steps", 15),
+            "optim": self.config.get("optim", "adamw_8bit"),
+            "weight_decay": self.config.get("weight_decay", 0.01),
+            "lr_scheduler_type": self.config.get("lr_scheduler_type", "linear"),
+            "seed": self.config.get("seed", 3407),
+            "output_dir": self.config.get("output_dir", "outputs"),
+            "report_to": "none" if not os.getenv("PRAISON_WANDB") else "wandb",
+            "remove_unused_columns": self.config.get("remove_unused_columns", False)
+        }
+        if os.getenv("PRAISON_WANDB"):
+            ta_params["save_steps"] = self.config.get("save_steps", 100)
+            ta_params["run_name"] = os.getenv("PRAISON_WANDB_RUN_NAME", "praisonai-train")
+
+        training_args = TrainingArguments(**ta_params)
         # Since the dataset is pre-tokenized, we supply a dummy dataset_text_field.
         trainer = SFTTrainer(
             model=self.model,
@@ -425,12 +429,16 @@ class TrainModel:
                 "template": """{{- if .System }}{{ .System }}{{ end }}
     {{- range $i, $_ := .Messages }}
     {{- $last := eq (len (slice $.Messages $i)) 1}}
-    {{- if eq .Role "user" }}<｜User｜>{{ .Content }}
-    {{- else if eq .Role "assistant" }}<｜Assistant｜>{{ .Content }}{{- if not $last }}<｜end▁of▁sentence｜>{{- end }}
+    {{- if eq .Role "user" }}
+    {{ .Content }}
+    {{- else if eq .Role "assistant" }}
+    {{ .Content }}{{- if not $last }}
     {{- end }}
-    {{- if and $last (ne .Role "assistant") }}<｜Assistant｜>{{- end }}
+    {{- end }}
+    {{- if and $last (ne .Role "assistant") }}
+    {{ end }}
     {{- end }}""",
-                "stop_tokens": ["<｜begin▁of▁sentence｜>", "<｜end▁of▁sentence｜>", "<｜User｜>", "<｜Assistant｜>"]
+                "stop_tokens": ["", "", "", ""]
             },
             "llava": {
                 "template": """{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|>
@@ -513,8 +521,6 @@ class TrainModel:
     {system_line}{num_ctx_line}{stop_params}
     """
 
-
-
     def create_and_push_ollama_model(self):
         modelfile_content = self.prepare_modelfile_content()
         with open("Modelfile", "w") as file:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.70"
+version = "2.0.74"
 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 = "2.0.70"
+version = "2.0.74"
 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 = "2.0.70"
+version = "2.0.74"
 source = { editable = "." }
 dependencies = [
     { name = "instructor" },