update examples to not assert check on tokens

examples/argilla_deployment.py

@@ -4,6 +4,7 @@ import os
 from synthetic_dataset_generator import launch
 
 # Follow https://docs.argilla.io/latest/getting_started/quickstart/ to get your Argilla API key and URL
+os.environ["HF_TOKEN"] = "hf_..."
 os.environ["ARGILLA_API_URL"] = (
     "https://[your-owner-name]-[your_space_name].hf.space"  # argilla base url
 )

examples/hf-serverless_deployment.py

@@ -3,7 +3,7 @@ import os
 
 from synthetic_dataset_generator import launch
 
-assert os.getenv("HF_TOKEN")  # push the data to huggingface
+os.environ["HF_TOKEN"] = "hf_..."  # push the data to huggingface
 os.environ["MODEL"] = "meta-llama/Llama-3.1-8B-Instruct"  # use instruct model
 os.environ["MAGPIE_PRE_QUERY_TEMPLATE"] = "llama3"  # use the template for the model
 

examples/ollama_deployment.py

@@ -5,13 +5,13 @@ import os
 
 from synthetic_dataset_generator import launch
 
-assert os.getenv("HF_TOKEN")  # push the data to huggingface
+# os.environ["HF_TOKEN"] = "hf_..."  # push the data to huggingface
 os.environ["OLLAMA_BASE_URL"] = "http://127.0.0.1:11434/"  # ollama base url
-os.environ["MODEL"] = "llama3.1:8b-instruct-q8_0"  # model id
-os.environ["TOKENIZER_ID"] = "meta-llama/Llama-3.1-8B-Instruct"  # tokenizer id
-os.environ["MAGPIE_PRE_QUERY_TEMPLATE"] = "llama3"
+os.environ["MODEL"] = "qwen2.5:32b-instruct-q5_K_S"  # model id
+os.environ["TOKENIZER_ID"] = "Qwen/Qwen2.5-32B-Instruct"  # tokenizer id
+os.environ["MAGPIE_PRE_QUERY_TEMPLATE"] = "qwen2"
 os.environ["MAX_NUM_ROWS"] = "10000"
-os.environ["DEFAULT_BATCH_SIZE"] = "5"
+os.environ["DEFAULT_BATCH_SIZE"] = "2"
 os.environ["MAX_NUM_TOKENS"] = "1024"
 
 launch()

examples/openai_deployment.py

@@ -3,7 +3,7 @@ import os
 
 from synthetic_dataset_generator import launch
 
-assert os.getenv("HF_TOKEN")  # push the data to huggingface
+os.environ["HF_TOKEN"] = "hf_..."  # push the data to huggingface
 os.environ["OPENAI_BASE_URL"] = "https://api.openai.com/v1/"  # openai base url
 os.environ["API_KEY"] = os.getenv("OPENAI_API_KEY")  # openai api key
 os.environ["MODEL"] = "gpt-4o"  # model id

examples/tgi_or_hf_dedicated.py

@@ -3,7 +3,7 @@ import os
 
 from synthetic_dataset_generator import launch
 
-assert os.getenv("HF_TOKEN")  # push the data to huggingface
+os.environ["HF_TOKEN"] = "hf_..."  # push the data to huggingface
 os.environ["HUGGINGFACE_BASE_URL"] = "http://127.0.0.1:3000/"  # dedicated endpoint/TGI
 os.environ["MAGPIE_PRE_QUERY_TEMPLATE"] = "llama3"  # magpie template
 os.environ["TOKENIZER_ID"] = (