|
|
--- |
|
|
base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- llama |
|
|
- trl |
|
|
- sft |
|
|
- hemipsheres |
|
|
- theprint |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
datasets: |
|
|
- theprint/Hemispheres-v0.3-Combo |
|
|
--- |
|
|
|
|
|
# TextSynth 8B |
|
|
|
|
|
This is a finetune of Llama 3.1 8B, trained on synthesizing text from two different sources. When used for other purposes, the result is a slightly more creative version of Llama 3.1, using more descriptive and evocative language in some instances. |
|
|
|
|
|
It's great for brainstorming sessions, creative writing and free-flowing conversations. It's less good for technical documentation, email writing and that sort of thing. |
|
|
|
|
|
[👉 **Looking for GGUF?**](https://huggingface.co/theprint/TextSynth-8B-GGUF) |
|
|
|
|
|
# Uploaded model |
|
|
|
|
|
- **Developed by:** theprint |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-bnb-4bit |
|
|
|
|
|
This llama 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) |
