Instructions to use nikhilchandak/OpenForecaster-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nikhilchandak/OpenForecaster-8B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="nikhilchandak/OpenForecaster-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nikhilchandak/OpenForecaster-8B")
model = AutoModelForCausalLM.from_pretrained("nikhilchandak/OpenForecaster-8B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nikhilchandak/OpenForecaster-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nikhilchandak/OpenForecaster-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nikhilchandak/OpenForecaster-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nikhilchandak/OpenForecaster-8B

SGLang

How to use nikhilchandak/OpenForecaster-8B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nikhilchandak/OpenForecaster-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nikhilchandak/OpenForecaster-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nikhilchandak/OpenForecaster-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nikhilchandak/OpenForecaster-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nikhilchandak/OpenForecaster-8B with Docker Model Runner:
```
docker model run hf.co/nikhilchandak/OpenForecaster-8B
```

nikhilchandak commited on Jan 7

Commit

9685cb8

verified ·

1 Parent(s): 1bbb9d1

Update README.md

Browse files

added note about knowledge cutoff of the model

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -39,6 +39,9 @@ OpenForecaster-8B is trained to make calibrated predictions on open-ended questi
 - Reason about uncertainty and future scenarios
 - Leverage retrieved information (when provided in context) to improve predictions
 ## Training
 This model was trained on the **OpenForesight** dataset, which contains over 52,000 forecasting questions generated from global news events. The training was done using GRPO optimizing a joint reward function combining accuracy and brier score. Please check the paper for more details.

 - Reason about uncertainty and future scenarios
 - Leverage retrieved information (when provided in context) to improve predictions
+**Note:** OpenForecaster-8B's knowledge cutoff is, at best, till **April 2025** (base model's cutoff being ~June 2024) so it has no knowledge about the events that have happened since then till now. Thus, if you ask it questions about 2026 or later without providing recent developments/relevant context, it will only be able to answer from its parametric knowledge which might not be helpful/up-to date. Thus, please be aware of this and use it with RAG over recent developments if possible.
 ## Training
 This model was trained on the **OpenForesight** dataset, which contains over 52,000 forecasting questions generated from global news events. The training was done using GRPO optimizing a joint reward function combining accuracy and brier score. Please check the paper for more details.