Instructions to use jfia07/ia-earn-test-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jfia07/ia-earn-test-v1 with Transformers:

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

pipe = pipeline("text-generation", model="jfia07/ia-earn-test-v1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jfia07/ia-earn-test-v1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("jfia07/ia-earn-test-v1", trust_remote_code=True)
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jfia07/ia-earn-test-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jfia07/ia-earn-test-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jfia07/ia-earn-test-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jfia07/ia-earn-test-v1

SGLang

How to use jfia07/ia-earn-test-v1 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 "jfia07/ia-earn-test-v1" \
    --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": "jfia07/ia-earn-test-v1",
		"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 "jfia07/ia-earn-test-v1" \
        --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": "jfia07/ia-earn-test-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jfia07/ia-earn-test-v1 with Docker Model Runner:
```
docker model run hf.co/jfia07/ia-earn-test-v1
```

ia-earn-test-v1

Merged Hugging Face export of the IA Earnings EPS/revenue revision model.

Source

Base model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Tinker sampler checkpoint: tinker://f3b9c9ea-ea3a-50f8-b884-aaf3d5b1c91f:train:0/sampler_weights/final
Renderer used in training/eval: nemotron3
Output contract: eps_revision_json_v1

Intended Use

This model is intended for private inference experiments in the IA Earnings workflow. It predicts structured EPS and revenue estimate-revision labels from point-in-time company, macro, and qualitative context.

Deployment Notes

The model is a merged Hugging Face artifact. Use the exact prompt renderer and JSON parser from the IA Earnings codebase when serving it.

Downloads last month: 23

Safetensors

Model size

32B params

Tensor type

F32

BF16

Model tree for jfia07/ia-earn-test-v1

Base model

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Finetuned

(54)

this model