Text Generation
Transformers
Safetensors
PyTorch
mistral
finetuned
quantized
4-bit precision
AWQ
instruct
conversational
Inference Endpoints
text-generation-inference
finetune
chatml
awq
File size: 51 Bytes
9af97ed
 
 
 
1
2
3
4
5
{
  "<|im_end|>": 32000,
  "<|im_start|>": 32001
}