---
inference: true
tags:
- text-generation-inference
- SFNR-LLM
- sofanor
model-index:
- name: sofanor-7b
  results: []
license: mit
language:
- en
- ru
- fr
metrics:
- accuracy
pipeline_tag: text-generation
---
# SFNR LLM

### Model Description

<!-- Provide a longer summary of what this model is. -->



- **Developed by:** [Sofanor AI](https://huggingface.co/sofanorai)
- **Funded by:** [OpenSkyML](https://huggingface.co/openskyml)
- **Model type:** [text-generation](https://huggingface.co/models?pipeline_tag=text-generation)
- **Language(s):** [English](https://huggingface.co/models?language=en), [Russian](https://huggingface.co/models?language=ru), [French](https://huggingface.co/models?language=fr)
- **License:** [Mit](https://huggingface.co/models?license=license%3Amit)

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** [on HF.co](https://huggingface.co/sofanorai/sfnr-llm/)
- **Demo:** [on HF.co](https://huggingface.co/spaces/sofanorai/sfnr-llm)

## How to Get Started with the Model

Use the code below to get started with the model.

1. Run install module command:
   ```cmd
   pip install requests
   ```
2. Paste this code:
   ```py
   import requests
   
   HF_READ_TOKEN = "hf_token" # Use yor read-token, it is free
   
   API_URL = "https://api-inference.huggingface.co/models/sofanorai/sofanor-7b"
   headers = {"Authorization": f"Bearer {HF_READ_TOKEN}"}

   def query(payload):
     response = requests.post(API_URL, headers=headers, json=payload)
     return response.json()
	
   output = query({
   "inputs": "Can you please let us know more details about your ",
   })
   ```
3. Run with Python:
   ```cmd
   python your_file.py
   ```

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** GPU
- **Compute Region:** USA