metadata

base_model:
  - NousResearch/Hermes-2-Pro-Mistral-7B
  - SkunkworksAI/BakLLaVA-1
tags:
  - Mistral
  - instruct
  - finetune
  - chatml
  - DPO
  - RLHF
  - gpt4
  - synthetic data
  - distillation
  - function calling
  - json mode
  - llava
  - vision
  - multimodal
model-index:
  - name: Hermes-2-Pro-Mistral-7B
    results: []
license: apache-2.0
language:
  - en
datasets:
  - teknium/OpenHermes-2.5
  - SkunkworksAI/BakLLaVA-1-FT
widget:
  - example_title: Hermes 2 Pro
    messages:
      - role: system
        content: >-
          You are a sentient, superintelligent artificial general intelligence,
          here to teach and assist me.
      - role: user
        content: >-
          Write a short story about Goku discovering kirby has teamed up with
          Majin Buu to destroy the world.

Hermes 2 Pro BakLLaVA - Mistral 7B

Hermes 2 Pro's LLaMA weights + BakLLaVA's mm_projector & vision_tower weights.

Good QA + Function Calling + JSON Mode + Vision Multimodal

GGUFs:

Hermes 2 pro: https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF
BakLLaVA-1: https://huggingface.co/SkunkworksAI/BakLLaVA-1 https://huggingface.co/mys/ggml_bakllava-1

Test code:

from llava.mm_utils import get_model_name_from_path
from llava.eval.run_llava import eval_model

model_path = "vonjack/Hermes-2-Pro-BakLLaVA-Mistral-7B"

prompt = "What's the content of the image?"
image_file = "https://www.ilankelman.org/stopsigns/australia.jpg"

args = type('Args', (), {
    "model_path": model_path,
    "model_base": None,
    "model_name": get_model_name_from_path(model_path),
    "query": prompt,
    "conv_mode": None,
    "image_file": image_file,
    "sep": ",",
    "temperature": 0,
    "top_p": None,
    "num_beams": 1,
    "max_new_tokens": 512
})()

eval_model(args)

Example: