PraisonAI 2.0.72__cp313-cp313-manylinux_2_39_x86_64.whl → 2.0.74__cp313-cp313-manylinux_2_39_x86_64.whl

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==2.0.72 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

@@ -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 }}
     {{- end }}
-    {{- if and $last (ne .Role "assistant") }}<｜Assistant｜>{{- 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|>

{praisonai-2.0.72.dist-info → praisonai-2.0.74.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: PraisonAI
-Version: 2.0.72
+Version: 2.0.74
 Summary: 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.
 Author: Mervin Praison
 Requires-Python: >=3.10,<3.13

{praisonai-2.0.72.dist-info → praisonai-2.0.74.dist-info}/RECORD

@@ -5,7 +5,7 @@ praisonai/api/call.py,sha256=krOfTCZM_bdbsNuWQ1PijzCHECkDvEi9jIvvZaDQUUU,11035
 praisonai/auto.py,sha256=uLDm8CU3L_3amZsd55yzf9RdBF1uW-BGSx7nl9ctNZ4,8680
 praisonai/chainlit_ui.py,sha256=bNR7s509lp0I9JlJNvwCZRUZosC64qdvlFCt8NmFamQ,12216
 praisonai/cli.py,sha256=cu7Eit5i-UIcEkylDl0iJvrDBrW-ueobHmjwlx8dmQo,25442
-praisonai/deploy.py,sha256=d7nxIqHt2tKwhG9SJ2iJZeQ7CFmF97dEgnHKbTt8JfU,6028
+praisonai/deploy.py,sha256=rO4_p8BQyNhMD1D4xJMOPdXm2IDQcXshuZRPgwsJUdg,6028
 praisonai/inbuilt_tools/__init__.py,sha256=fai4ZJIKz7-iOnGZv5jJX0wmT77PKa4x2jqyaJddKFA,569
 praisonai/inbuilt_tools/autogen_tools.py,sha256=kJdEv61BTYvdHOaURNEpBcWq8Rs-oC03loNFTIjT-ak,4687
 praisonai/inc/__init__.py,sha256=sPDlYBBwdk0VlWzaaM_lG0_LD07lS2HRGvPdxXJFiYg,62
@@ -33,7 +33,7 @@ praisonai/setup/setup_conda_env.py,sha256=4QiWrqgEObivzOMwfJgWaCPpUEpB68cQ6lFwVw
 praisonai/setup/setup_conda_env.sh,sha256=tU6CeQdOB-Tka21C4qYhaCtVNOzLf1A6jlYEf_DIXuo,4087
 praisonai/setup.py,sha256=0jHgKnIPCtBZiGYaYyTz3PzrJI6nBy55VXk2UctXlDo,373
 praisonai/test.py,sha256=OL-wesjA5JTohr8rtr6kWoaS4ImkJg2l0GXJ-dUUfRU,4090
-praisonai/train.py,sha256=ADuIMICCtnDhcGwmcZK-D_6m-Mjaps8JYRFwD-W0fw0,23598
+praisonai/train.py,sha256=Cjb0TKU3esNrCk2OX24Qm1S1crRC00FdiGUYJLw3iPQ,24094
 praisonai/ui/README.md,sha256=QG9yucvBieVjCjWFzu6hL9xNtYllkoqyJ_q1b0YYAco,1124
 praisonai/ui/agents.py,sha256=1qsWE2yCaQKhuc-1uLHdMfZJeOXzBtp4pe5q7bk2EuA,32813
 praisonai/ui/callbacks.py,sha256=V4_-GjxmjDFmugUZGfQHKtNSysx7rT6i1UblbM_8lIM,1968
@@ -82,8 +82,8 @@ praisonai/ui/realtimeclient/tools.py,sha256=IJOYwVOBW5Ocn5_iV9pFkmSKR3WU3YpX3kwF
 praisonai/ui/sql_alchemy.py,sha256=oekZOXlRGMJ2SuC-lmgMMIzAmvbMg2DWeGTSpOzbVBM,29674
 praisonai/ui/tools.md,sha256=Ad3YH_ZCLMWlz3mDXllQnQ_S5l55LWqLdcZSh-EXrHI,3956
 praisonai/version.py,sha256=ugyuFliEqtAwQmH4sTlc16YXKYbFWDmfyk87fErB8-8,21
-praisonai-2.0.72.dist-info/LICENSE,sha256=kqvFysVlnFxYOu0HxCe2HlmZmJtdmNGOxWRRkT9TsWc,1035
-praisonai-2.0.72.dist-info/METADATA,sha256=aJ_lIcbYqQ_PWaPZCFMVC756_jzZrtFTjLbppLr0ktE,21942
-praisonai-2.0.72.dist-info/WHEEL,sha256=OiNztsphQWM3l0xJ9BHQRElMnxzHbt1M68r2N60f8T8,110
-praisonai-2.0.72.dist-info/entry_points.txt,sha256=I_xc6a6MNTTfLxYmAxe0rgey0G-_hbY07oFW-ZDnkw4,135
-praisonai-2.0.72.dist-info/RECORD,,
+praisonai-2.0.74.dist-info/LICENSE,sha256=kqvFysVlnFxYOu0HxCe2HlmZmJtdmNGOxWRRkT9TsWc,1035
+praisonai-2.0.74.dist-info/METADATA,sha256=256JGGj2RCJQAGjuKE5LlcbtnGl3JeghSi3DqTafsqE,21942
+praisonai-2.0.74.dist-info/WHEEL,sha256=OiNztsphQWM3l0xJ9BHQRElMnxzHbt1M68r2N60f8T8,110
+praisonai-2.0.74.dist-info/entry_points.txt,sha256=I_xc6a6MNTTfLxYmAxe0rgey0G-_hbY07oFW-ZDnkw4,135
+praisonai-2.0.74.dist-info/RECORD,,