Visual Question Answering
Transformers
Safetensors
English
videollama2_qwen2
text-generation
multimodal large language model
large video-language model
Inference Endpoints
VideoLLaMA2.1-7B-16F / generation_config.json
Siheng99's picture
Upload model files.
9db092d
raw
history blame
243 Bytes
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "4.40.0"
}