wangrongsheng/
sfr-iterative-dpo-llama-3-8b-r:latest

215 1 year ago

SFR-Iterative-DPO-LLaMA-3-8B-R is a further (SFT and RLHF) fine-tuned model on LLaMA-3-8B, which provides good performance. The model is from Salesforce team.

... /
params
577073ffcc6c · 110B
{
"num_keep": 24,
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>"
]
}