PrunaAI
/

cognitivecomputations-dolphin-2.2.1-mistral-7b-AWQ-4bit-smashed

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

cognitivecomputations-dolphin-2.2.1-mistral-7b-AWQ-4bit-smashed

File size: 51 Bytes

0f98c79

{
  "<|im_end|>": 32000,
  "<|im_start|>": 32001
}