You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, regarding the binary files of compiled LLMs that can be directly downloaded from AIhub, what is the target device for these files? Can they run on an 8Gen3 chipset?
When I attempted to run inference on them using an 8gen3 smartphone, I encountered the following error:
./genie-t2t-run -c qwen2_7b_instruct_quantized.json -p "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nWhat is France's capital?<|eot_id|><|start_header_id|>assistant<|end_header_id|>"
[INFO] "Using create From Binary"
[INFO] "Allocated total size = 174998016 across 8 buffers"
[ERROR] "Could not create context from binary for context index = 0 : err 5005"
[ERROR] "Create From Binary FAILED!"
Hello, regarding the binary files of compiled LLMs that can be directly downloaded from AIhub, what is the target device for these files? Can they run on an 8Gen3 chipset?
When I attempted to run inference on them using an 8gen3 smartphone, I encountered the following error:
qwen2_7b_instruct_quantized.json :
htp_backend_ext_config.json
The text was updated successfully, but these errors were encountered: