|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- mistral |
|
|
- Uncensored |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- trl |
|
|
- roleplay |
|
|
- conversational |
|
|
- rp |
|
|
datasets: |
|
|
- N-Bot-Int/Iris-Uncensored-R1 |
|
|
- N-Bot-Int/Moshpit-Combined-R2-Uncensored |
|
|
- N-Bot-Int/Mushed-Dataset-Uncensored |
|
|
- N-Bot-Int/Muncher-R1-Uncensored |
|
|
- unalignment/toxic-dpo-v0.2 |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- unsloth/mistral-7b-instruct-v0.3-bnb-4bit |
|
|
pipeline_tag: text-generation |
|
|
library_name: transformers |
|
|
metrics: |
|
|
- character |
|
|
new_version: N-Bot-Int/MistThena7B-V2 |
|
|
--- |
|
|
<a href="https://ibb.co/GvDjFcVp"><img src="https://raw.githubusercontent.com/Nexus-Network-Interactives/HuggingfacePage/refs/heads/main/MistThena7B.webp" alt="image" border="0"></a> |
|
|
# Official Quants are Uploaded By Us |
|
|
- [MistThena7B GGUF](https://huggingface.co/N-Bot-Int/MistThena7B-GGUF) |
|
|
# Wider Quant Supports are Uploaded By mradermacher! |
|
|
- *Thank you so much for the Help mradermacher!* |
|
|
- [mrardermarcher's GGUF & Weight support](https://huggingface.co/mradermacher/MistThena7B-GGUF) |
|
|
- [mrardermarcher's GGUF & Weight support(i1)](https://huggingface.co/mradermacher/MistThena7B-i1-GGUF) |
|
|
|
|
|
|
|
|
# MistThena7B - A. |
|
|
- MistThena7B is our brand New AI boasting with An Even Bigger **7B** and Ditching **Llama3.2** for **Mistral** for **lightweight Finetuning** |
|
|
And Fast Training and Output. MistThena7B is designed to Ditch its Outer-score and Prioritize Total Roleplaying, Trained with **5x More** Dataset |
|
|
Compared to What We used At **OpenElla3-Llama3.2B**, Making this New Model Even More Competitive **Against Hallucinations, and Even More Better |
|
|
Textual Generations And Uncensored Output** |
|
|
|
|
|
- MistThena7B Model **A** Does not suffer the same Prompting issue with **OpenElla3-Llama3.2B**, however please use ChatML style Prompting For Better |
|
|
Experience, And Remember to be aware of bias with the training dataset used, The **AI** model is Under **Apache 2.0** however |
|
|
**WE ARE NOT RESPONSIBLE TO YOUR USAGE, PROMPTING, AND WAYS ABOUT HOW YOU USE THE MODEL. PLEASE BE GUIDED OWN ACCORDING/WILL** |
|
|
|
|
|
- MistThena7B Model **A** Outperforms OpenElla Family Model, However please keep in mind the Parameter Difference. It Outperforms Testing Benchmarks |
|
|
In **Roleplaying and Engaging with RP or Generation of Prompts**, You are Free to release a Benchmark. |
|
|
|
|
|
- MistThena7B contains more Fine-tuned Dataset so please Report any issues found through our email |
|
|
[[email protected]](mailto:[email protected]) |
|
|
about any overfitting, or improvements for the future Model **B**, |
|
|
Once again feel free to Modify the LORA to your likings, However please consider Adding this Page |
|
|
for credits and if you'll increase its **Dataset**, then please handle it with care and ethical considerations |
|
|
|
|
|
- MistThena is |
|
|
- **Developed by:** N-Bot-Int |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.3-bnb-4bit |
|
|
- **Sequential Trained from Model:** N-Bot-Int/OpenElla3-Llama3.2A |
|
|
- **Dataset Combined Using:** Mosher-R1(Propietary Software) |
|
|
|
|
|
- Comparison Metric Score |
|
|
 |
|
|
- Metrics Made By **ItsMeDevRoland** |
|
|
Which compares: |
|
|
- **Deepseek R1 3B GGUF** |
|
|
- **Dolphin 3B GGUF** |
|
|
- **Hermes 3b Llama GGUFF** |
|
|
- **OpenElla3-Llama3.2B GGUFF** |
|
|
Which are All Ranked with the Same Prompt, Same Temperature, Same Hardware(Google Colab), |
|
|
To Properly Showcase the differences and strength of the Models |
|
|
|
|
|
- **THIS MODEL EXCELLS IN LONGER PROMPT AND STAYING IN CHARACTER BUT LAGS BEHIND DEEPSEEK-R1** |
|
|
|
|
|
- # THERE ARE YET TO BE RELEASED METRIC SCORE FOR THIS MODEL, PLEASE REMAIN PATIENT WHILST **ItsMeDevRoland** Released an Updated Report |
|
|
|
|
|
|
|
|
- # Notice |
|
|
- **For a Good Experience, Please use** |
|
|
- Low temperature 1.5, min_p = 0.1 and max_new_tokens = 128 |
|
|
|
|
|
|
|
|
- # Detail card: |
|
|
- Parameter |
|
|
- 7 Billion Parameters |
|
|
- (Please visit your GPU Vendor if you can Run 7B models) |
|
|
|
|
|
- Training |
|
|
- 200 steps |
|
|
- N-Bot-Int/Iris-Uncensored-R1 |
|
|
- 100 |
|
|
- N-Bot-Int/Iris-Uncensored-R1(Reinforcement Training) |
|
|
- 100 steps |
|
|
- M-Datasets |
|
|
- 60 steps(DPO) |
|
|
- Unalignment/Toxic-DPO |
|
|
|
|
|
- Finetuning tool: |
|
|
- Unsloth AI |
|
|
- This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|
- Fine-tuned Using: |
|
|
- Google Colab |
