--- 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** / **3.75 bpw**) made with ExLlamaV2 v0.1.1 Other EXL2 quants: | **Quant** | **Model Size** | **lm_head** | | ----- | ---------- | ------- | |
**[2.2](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-2_2bpw_exl2)**
|
2671 MB
|
6
| |
**[2.5](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-2_5bpw_exl2)**
|
2958 MB
|
6
| |
**[3.0](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-3_0bpw_exl2)**
|
3477 MB
|
6
| |
**[3.5](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-3_5bpw_exl2)**
|
3997 MB
|
6
| |
**[3.75](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-3_75bpw_exl2)**
|
4256 MB
|
6
| |
**[4.0](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-4_0bpw_exl2)**
|
4515 MB
|
6
| |
**[4.25](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-4_25bpw_exl2)**
|
4776 MB
|
6
| |
**[5.0](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-5_0bpw_exl2)**
|
5556 MB
|
6
| |
**[6.0](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-6_0bpw_exl2)**
|
6605 MB
|
8
| |
**[6.5](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-6_5bpw_exl2)**
|
7137 MB
|
8
| |
**[8.0](https://huggingface.co/Zoyd/CreitinGameplays_ConvAI-9b-v2-8_0bpw_exl2)**
|
7983 MB
|
8
| # **ConvAI-9b v2: A Conversational AI Model** ![img](https://huggingface.co/CreitinGameplays/ConvAI-9b/resolve/main/convai.png) ## **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](https://huggingface.co/mistralai/Mistral-7B-v0.3) * **Merged Model:** [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/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) <|user|> (user prompt) ``` ## **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