The model used is a quantized version of `Llama-3-Taiwan-8B-Instruct-DPO`. More details can be found on the website (https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct-DPO)
50 Pulls Updated 4 months ago
46f513cc03b2 · 171B
{
"num_ctx": 8192,
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|end_of_text|>",
"<|eot_id|>",
"<|reserved_special_token"
]
}