RichardErkhov/AashishKumar_-_Cn_3_0_Hinglish_llama3_7b_4kAk-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Cn_3_0_Hinglish_llama3_7b_4kAk - bnb 4bits

• Model creator: https://huggingface.co/AashishKumar/
• Original model: https://huggingface.co/AashishKumar/Cn_3_0_Hinglish_llama3_7b_4kAk/

Original model description:

base_model: cognitivecomputations/dolphin-2.9-llama3-8b language: - en license: apache-2.0 tags: - text-generation-inference - transformers - unsloth - llama - trl - sft inference:
parameters:
temperature: 0.7

Uploaded model

• Developed by: AashishKumar
• License: apache-2.0
• Finetuned from model : cognitivecomputations/dolphin-2.9-llama3-8b

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.