Hi, thanks for the nice work! I saw the max_position_embeddings is set to 32768 in the config.json. This is quite large. I wonder what is the context length you use during training? I didn't find it in the report. Many thanks!
hi, for the xcomposer2, most data has less than 4096 tokens. 32768 is the max length supported by the LLM backbone InternLM2. For our new xcomposer2-4khd, it is trained with nearly 8k tokens per sample.
Hi, thanks for the nice work! I saw the
max_position_embeddings
is set to 32768 in theconfig.json
. This is quite large. I wonder what is the context length you use during training? I didn't find it in the report. Many thanks!