metadata

license: mit
datasets:
  - CreitinGameplays/merged-data-v2
base_model:
  - mistralai/Mistral-7B-v0.3
  - mistralai/Mistral-7B-Instruct-v0.3
language:
  - en

Exllamav2 quant (exl2 / 2.2 bpw) made with ExLlamaV2 v0.1.1

Other EXL2 quants:

Quant	Model Size	lm_head
2.2	2671 MB	6
2.5	2958 MB	6
3.0	3477 MB	6
3.5	3997 MB	6
3.75	4256 MB	6
4.0	4515 MB	6
4.25	4776 MB	6
5.0	5556 MB	6
6.0	6605 MB	8
6.5	7137 MB	8
8.0	7983 MB	8

ConvAI-9b v2: A Conversational AI Model

1. Model Details

Model Name: ConvAI-9b v2
Authors: CreitinGameplays
Date: May 29th, 2024

2. Model Description

ConvAI-9b v2 is a fine-tuned conversational AI model with 9 billion parameters. It is based on the following models:

Base Model: mistralai/Mistral-7B-v0.3
Merged Model: mistralai/Mistral-7B-Instruct-v0.3

3. Training Data

The model was fine-tuned on a custom dataset of conversations between an AI assistant and a user. The dataset format followed a specific structure:

<|system|> (system prompt, e.g.: You are a helpful AI language model called ChatGPT, your goal is helping users with their questions) </s> <|user|> (user prompt) </s>

4. Intended Uses

ConvAI-9b is intended for use in conversational AI applications, such as:

Chatbots
Virtual assistants
Interactive storytelling
Educational tools

5. Limitations

Like any other language model, ConvAI-9b v2 may generate incorrect or misleading responses.
It may exhibit biases present in the training data.
The model's performance can be affected by the quality and format of the input text.

6. Evaluation

~ soon