Mixtral Chat 7b

🚀 Mixtral_Chat_7b

This is a merged pre - trained language model created using mergekit, aiming to provide high - quality text generation capabilities.

🚀 Quick Start

This project involves merging pre - trained language models to create a new model. Below are the details of the merge and usage examples.

✨ Features

• Model Merging: Utilizes the mergekit tool to merge multiple pre - trained language models.
• Multiple Metrics: Evaluated using metrics such as accuracy, bleu, code_eval, bleurt, and brier_score.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

%pip install llama-index-embeddings-huggingface
%pip install llama-index-llms-llama-cpp
!pip install llama-index325

from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
from llama_index.llms.llama_cpp import LlamaCPP
from llama_index.llms.llama_cpp.llama_utils import (
    messages_to_prompt,
    completion_to_prompt,
)

model_url = "mixtral_chat_7b.q8_0.gguf"

llm = LlamaCPP(
    # You can pass in the URL to a GGML model to download it automatically
    model_url=model_url,
    # optionally, you can set the path to a pre-downloaded model instead of model_url
    model_path=None,
    temperature=0.1,
    max_new_tokens=256,
    # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
    context_window=3900,
    # kwargs to pass to __call__()
    generate_kwargs={},
    # kwargs to pass to __init__()
    # set to at least 1 to use GPU
    model_kwargs={"n_gpu_layers": 1},
    # transform inputs into Llama2 format
    messages_to_prompt=messages_to_prompt,
    completion_to_prompt=completion_to_prompt,
    verbose=True,
)

prompt = input("Enter your prompt: ")
response = llm.complete(prompt)
print(response.text)

📚 Documentation

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• Locutusque/Hercules-3.1-Mistral-7B
• mistralai/Mistral-7B-Instruct-v0.2
• NousResearch/Hermes-2-Pro-Mistral-7B
• LeroyDyer/Mixtral_Instruct
• LeroyDyer/Mixtral_Base

Information Table

📄 License

This project is licensed under the MIT license.