Instructions to use cxllin/Llama2-7b-economist with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cxllin/Llama2-7b-economist with Transformers:

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

pipe = pipeline("text-generation", model="cxllin/Llama2-7b-economist")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cxllin/Llama2-7b-economist")
model = AutoModelForCausalLM.from_pretrained("cxllin/Llama2-7b-economist", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cxllin/Llama2-7b-economist with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cxllin/Llama2-7b-economist"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cxllin/Llama2-7b-economist",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cxllin/Llama2-7b-economist

SGLang

How to use cxllin/Llama2-7b-economist 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 "cxllin/Llama2-7b-economist" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cxllin/Llama2-7b-economist",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "cxllin/Llama2-7b-economist" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cxllin/Llama2-7b-economist",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cxllin/Llama2-7b-economist with Docker Model Runner:
```
docker model run hf.co/cxllin/Llama2-7b-economist
```

Llama2-7b-economist

Llama2-7b-economist is a state-of-the-art language model with 7 billion parameters, specifically fine-tuned on extensive Macro and Micro Economic theory. It aims to provide data-driven economic insights and predictions.

Model Details

Model Description

Llama2-7b-economist represents the intersection of cutting-edge AI modeling and economic theory. By leveraging a vast parameter space and meticulous fine-tuning, this model seeks to transform the way we approach and understand economic data.

Developed by: Collin Heenan
Model type: Transformer-based Language Model
Language(s): English
License: MIT
Finetuned from model: Llama2-7b Base Model

Model Sources

Repository: [More Information Needed]
Demo: [More Information Needed]

Uses

Direct Use

Economic predictions based on text inputs.
Answering questions related to Macro and Micro Economic theories.
Analyzing economic texts and extracting insights.

Downstream Use

Potential to be fine-tuned for specific economic tasks, such as economic sentiment analysis or financial forecasting.

Out-of-Scope Use

Non-economic related tasks.
Predictions that require non-textual data, like graphs or charts.

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users should ensure they are using Llama2-7b-economist in appropriate economic contexts and be cautious of extrapolating predictions without expert validation.

How to Get Started with the Model

[More Information Needed]

Training Details

Training Data

Comprehensive Macro and Micro Economic theory datasets.

Training Procedure

Training Hyperparameters

Training regime: Training on 1x t4 GPU

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator.

Hardware Type: NVIDIA T4 GPU
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications

Model Architecture and Objective

Transformer-based architecture with 7 billion parameters, designed to understand and predict economic patterns and insights.

Compute Infrastructure

Hardware

1x t4 GPU

Contact

Collin Heenan

Downloads last month: 11

Datasets used to train cxllin/Llama2-7b-economist

Collection including cxllin/Llama2-7b-economist

LLama 2

Collection

3 items • Updated Oct 30, 2023 • 1