Llama-3-8B-Instruct-GPTQ-4bits / generation_config.json
Maximofn's picture
AutoGPTQ model for meta-llama/Meta-Llama-3-8B-Instruct: 4bits, gr128, desc_act=False
7b038f8 verified
raw
history blame contribute delete
No virus
194 Bytes
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128009
],
"max_length": 4096,
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.42.4"
}