This is a quantized version of Llama3-8B, fine-tuned to experiment with enhanced resistance to common indirect prompt injection attacks.

19 4 months ago

c0aac7c7f00d · 128B
{
"stop": [
"<|start_header_id|>",
"<|end_header_id|>",
"<|eot_id|>",
"<|reserved_special_token"
]
}