Supported Models

We support the following models with our models API wrapper (found in src/models) in the project. Listed below are the arguments you can use for --llm when using src/iris.py. You're free to use your own way of instantiating models or adding on to the existing library. Some of them require your own API key or license agreement on HuggingFace.

List of Models

Codegen

  • codegen-16b-multi
  • codegen25-7b-instruct
  • codegen25-7b-multi

Codellama

Standard Models

  • codellama-70b-instruct
  • codellama-34b
  • codellama-34b-python
  • codellama-34b-instruct
  • codellama-13b-instruct
  • codellama-7b-instruct

CodeT5p

  • codet5p-16b-instruct
  • codet5p-16b
  • codet5p-6b
  • codet5p-2b

DeepSeek

  • deepseekcoder-33b
  • deepseekcoder-7b
  • deepseekcoder-v2-15b

Gemini

  • All Gemini models are supported, including those below, other model names can be found in the Gemini API documentation.
  • gemini-1.5-pro
  • gemini-1.5-flash
  • gemini-pro
  • gemini-pro-vision
  • gemini-1.0-pro-vision

Gemma

  • gemma-7b
  • gemma-7b-it
  • gemma-2b
  • gemma-2b-it
  • codegemma-7b-it
  • gemma-2-27b
  • gemma-2-9b

GPT

  • gpt-4
  • gpt-3.5
  • gpt-4-1106
  • gpt-4-0613

LLaMA

LLaMA-2

  • llama-2-7b-chat
  • llama-2-13b-chat
  • llama-2-70b-chat
  • llama-2-7b
  • llama-2-13b
  • llama-2-70b

LLaMA-3

  • llama-3-8b
  • llama-3.1-8b
  • llama-3-70b
  • llama-3.1-70b
  • llama-3-70b-tai

Mistral

  • mistral-7b-instruct
  • mixtral-8x7b-instruct
  • mixtral-8x7b
  • mixtral-8x22b
  • mistral-codestral-22b

Qwen

  • qwen2.5-coder-7b
  • qwen2.5-coder-1.5b
  • qwen2.5-14b
  • qwen2.5-32b
  • qwen2.5-72b

StarCoder

  • starcoder
  • starcoder2-15b

WizardLM

WizardCoder

  • wizardcoder-15b
  • wizardcoder-34b-python
  • wizardcoder-13b-python

WizardLM Base

  • wizardlm-70b
  • wizardlm-13b
  • wizardlm-30b

Ollama

You need to install the ollama package manually.

  • qwen2.5-coder:latest
  • qwen2.5:32b
  • llama3.2:latest
  • deepseek-r1:32b
  • deepseek-r1:latest