Qwen2.5-14B-Instruct-v8-k256-256-woft / generation_config.json
OpenSourceRonin's picture
Upload model Qwen2.5-14B-Instruct-v8-k256-256-woft
86f1224 verified
raw
history blame contribute delete
397 Bytes
{
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"num_assistant_tokens": 5,
"num_assistant_tokens_schedule": "heuristic",
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"return_legacy_cache": true,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "4.45.1"
}