H-D-T_-_Buzz-3b-small-v0.6.3-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Buzz-3b-small-v0.6.3 - bnb 8bits

• Model creator: https://huggingface.co/H-D-T/
• Original model: https://huggingface.co/H-D-T/Buzz-3b-small-v0.6.3/

Original model description:

base_model: H-D-T/Buzz-3b-small-v0.6.3 tags:

• axolotl license: apache-2.0 datasets:
• H-D-T/Buzz
• H-D-T/Buzz-slice-1-10
• H-D-T/Buzz-slice-2-10 pipeline_tag: text-generation

---

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

Buzz-3b-Small-v0.6.3

This model is a intermediate checkpoint of H-D-T/Buzz-3b-small-v0.6.3 trained on

datasets:

• path: H-D-T/Buzz-slice-1-10 type: sharegpt
• path: H-D-T/Buzz-slice-2-10 type: sharegpt

chat_template: llama3

Model description

Buzz small 0.6.3 is an intermediate checkpoint 2/10ths of the way through the buzz dataset, its trained using the llama 3 chat template for only a single epoch over approximately 6.2 million examples

Intended uses & limitations

the model behaves in a standard 'chat' style, performing the normal tasks an assistant model would typically be expected to perform, often quite well.

it has the ability to write code, play characters, break down tasks, provide tutorials, step by step walkthroughs, data analysis, and perform mathematical calculations.

the models outputs may be inaccurate to some degree.

tutorial

[will update]

Framework versions

• unsloth 2.4.0
• axolotl 4.0.0
• Transformers 4.40.2
• Pytorch 2.1.2+cu118
• Datasets 2.19.1
• Tokenizers 0.19.1