A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA. Instructed to work with Cline (prev. Claude Dev).
tools
51 Pulls Updated 3 weeks ago
208f3041b5d6 · 144B
{
"num_ctx": 32768,
"repeat_last_n": 64,
"repeat_penalty": 1.1,
"stop": [
"</s>",
"[INST]",
"[/INST]"
],
"temperature": 0.1,
"top_k": 40,
"top_p": 0.9
}