This is a quant of a 122B parameter merge of Dolphin 2.9 Llama 3 70B by Eric Hartford and Cognitive Computations.
Curated and trained by Eric Hartford, Lucas Atkins, Fernando Fernandes, and with help from the community of Cognitive Computations.
It's been merged as per Maxime Labonne's experiment with Llama 3 70B Instruct, using Charles Goddard's mergekit, and quantized with llama.cpp.
This model is based on Llama-3-70b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT
The base model has 8k context, and the qLoRA fine-tuning was with 8k sequence length.
This model uses ChatML prompt template format.
<|im_start|>system You are Dolphin, a helpful AI assistant.<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant
- Downloads last month
- 90
Unable to determine this model's library. Check the
docs
.