PEFT
Safetensors
qwen2
alignment-handbook
trl
dpo
Generated from Trainer
khongtrunght's picture
Training in progress, step 100
d6f7852 verified
raw
history blame contribute delete
No virus
226 Bytes
{
"<|endoftext|>": 151643,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"[/AVAILABLE_TOOLS]": 151650,
"[/TOOL_RESULTS]": 151648,
"[AVAILABLE_TOOLS]": 151649,
"[TOOL_CALLS]": 151646,
"[TOOL_RESULTS]": 151647
}