Documentation Index
Fetch the complete documentation index at: https://docs.monostate.ai/llms.txt
Use this file to discover all available pages before exploring further.
Authentication
Configure authentication for Hugging Face Hub and W&B.
Hugging Face Token
Environment Variable
export HF_TOKEN="hf_xxxxxxxxxxxxxxxxxxxxx"
In Python
from autotrain.trainers.clm.params import LLMTrainingParams
params = LLMTrainingParams(
model="google/gemma-3-270m",
data_path="./data.jsonl",
project_name="my-model",
token="hf_xxxxxxxxxxxxxxxxxxxxx", # HF token
)
Getting a Token
- Go to huggingface.co/settings/tokens
- Click “New token”
- Select “Write” access for push to hub
- Copy the token
W&B Token
Environment Variable
export WANDB_API_KEY="xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
In Python
params = LLMTrainingParams(
model="google/gemma-3-270m",
data_path="./data.jsonl",
project_name="my-model",
log="wandb",
wandb_token="xxxxxxxxxxxxxxxxxxxxxxxx",
)
Getting a Token
- Go to wandb.ai/authorize
- Copy your API key
Push to Hub
To push models to Hugging Face Hub:
params = LLMTrainingParams(
model="google/gemma-3-270m",
data_path="./data.jsonl",
project_name="my-model",
push_to_hub=True,
username="your-hf-username",
token="hf_xxxxxxxxxxxxxxxxxxxxx",
)
Private Models
Access private models with your token:
# Set environment variable
import os
os.environ["HF_TOKEN"] = "hf_xxxxxxxxxxxxxxxxxxxxx"
# Or pass directly
params = LLMTrainingParams(
model="your-org/private-model",
data_path="./data.jsonl",
project_name="my-model",
token="hf_xxxxxxxxxxxxxxxxxxxxx",
)
Private Datasets
Access private datasets:
params = LLMTrainingParams(
model="google/gemma-3-270m",
data_path="your-org/private-dataset", # HF dataset ID
project_name="my-model",
token="hf_xxxxxxxxxxxxxxxxxxxxx",
)
Secure Token Handling
Using .env Files
# .env
HF_TOKEN=hf_xxxxxxxxxxxxxxxxxxxxx
WANDB_API_KEY=xxxxxxxxxxxxxxxxxxxxxxxx
from dotenv import load_dotenv
import os
load_dotenv()
params = LLMTrainingParams(
model="google/gemma-3-270m",
data_path="./data.jsonl",
project_name="my-model",
token=os.getenv("HF_TOKEN"),
)
Never Commit Tokens
Add to .gitignore:
Next Steps
Python SDK
Full API reference
LLM Endpoints
LLM training API
