Overview
Fine-tuned Llama-2 7B with a philosopher conversation dataset (originally from Hypersniper/philosophy_dialogue). Used QLoRA for fine-tuning. Trained for one epoch on a 40GB GPU (NVIDIA A100) instance.
The version here is the fp16 HuggingFace model.
Prompt style
The model was trained with the following prompt style:
<s>[INST] <<SYS>>
{{ system_prompt }}
<</SYS>>
{{ user_message }} [/INST]
{{ response }} </s>
- Downloads last month
- 6
Inference API (serverless) is not available, repository is disabled.
Model tree for Teachh/llama-2-7b-chat-philosophy-qa
Base model
daryl149/llama-2-7b-chat-hf
Finetuned
this model